CHI 2000 Workshop on Natural Language Interfaces

The Hague, The Netherlands, April 3, 2000

 

 

Motivating the cross-fertilization between HCI and Natural Language Processing

 

Cécile Paris and Nadine Ozkan

CSIRO/MIS

Locked bag 17, North Ryde

NSW 1670, Australia

email: {firstname.lastname@cmis.csiro.au}

 

1. Introduction

 

Over the past few years, our research group has been comprised of researchers from both the Human-Computer Interaction (HCI) and the Natural Language Processing (NLP) communities, and we have thus been exploring how the two communities can benefit each other. In this position paper, we present our views on this topic, as well as some examples of how the two disciplines meet in specific projects. Our expertise in NLP is mostly in a sub-area, namely Natural Language Generation (NLG), in which one is concerned with producing text. Our discussion will thus focus on the relationships that can exist between HCI and NLG.

 

 

2. Methodologies and theories from the two disciplines can complement each other

 

HCI and NLG have different methodologies and theories.  For example, one important methodology in HCI is the user-centered design approach, in which a user requirement analysis and potentially a task modeling analysis are done through observations, focus groups, story-boarding, etc. In contrast, the most accepted methodology in NLG research is corpus analysis, where a set of representative human-authored texts is collected and analysed in depth. Corpus analysis is used to identify the characteristics of the target texts in terms of textual, semantic, lexical and syntactic attributes. It seems to us that both communities would benefit from using each other’s methodology in specific contexts.

 

2.1 Complementing corpus analysis with a user-centered design approach

 

NLG is concerned with developing systems that produce texts (in a broad sense: written or verbal, self-contained or as part of a human-machine dialogue).  These systems are mostly designed by NLG experts and in the absence of HCI expertise. Consequently, the design method used tends to be solely corpus analysis, which provides the target text the system should emulate, and questions of interaction proper are often disregarded. Sometimes, a corpus of the probable input to the system is also collected, and the problem becomes characterizing the mapping that must take place. This still ignores some of the interaction issues that ought to be addressed to design a system.  We thus argue that, while corpus analysis does have its utility, it also has limitations for the design of a system, because it is only concerned with the system’s output.  A design perspective based solely on the required output is insufficient for good usability. We explore these limitations more fully below.

 

First, the corpus is often a collection of texts which, depending on how they are obtained and annotated, may be removed from their broader context of use (e.g., the environment in which the text was produced and understood). It is precisely this broad context of use that is being addressed in a user-centered approach to design, and it would be beneficial to add this dimension for the design of a generation system.

 

The second limitation concerns the fact that the texts in the corpus are human-authored.  A generation system then tries to emulate these texts. Yet, the texts generated by a machine will not be like those written by authors. We can expect that, given a machine-generated text, the reader’s expectations will be different from the expectations regarding human-authored texts. Thus, the texts in the corpus should not be the only objects of study for the design of the NLG system. The corpus study should be complemented by a study centered on users and their interaction with the potential generated text.

 

More generally, researchers in NLP take human-human communication as their model. Yet, the introduction of the computer into this communication, or the replacement of one of the participants by a computer changes the interaction, and potentially also changes user expectations and behavior. It is indeed not clear that a user would “talk to”, or interact with, a computer in the same way as he or she does with another human being, at least not given the current technology.  Therefore, researchers designing NLG systems may benefit from elucidating users expectations regarding generated text, thus complementing their approach with the types of analysis done in HCI.

 

Finally, an NLG system, just like any other system, should be designed with the user in mind. Issues often studied in HCI are important in that context, and they are not necessarily studied by looking at the language to be produced. Examples in the context of a speech system include:

·        ensuring that the user’s expectations regarding the scope of the system are set appropriately at the beginning of an interaction;

·        determining whether switching from a pre-recorded set of utterances – e.g., the introductory message – to an utterance produced from a synthesizer is likely to confuse the hearer.

While the texts produced are of course an important aspect of an NLG system, they do not appear in isolation nor form the whole system. The system’s context of use, and the users of that system are also important.

 

2.2 Using a corpus analysis as part of an HCI study

 

While corpus analysis has the limitations we have just outlined, it can be a valuable tool for HCI practitioners. After all, one of HCI’s strong principles is to speak the user’s language. Corpus analysis can refine the knowledge that current HCI methods yield, so as to capture not only individual words and idioms used by the user population, but also the syntax, level of language, etc.  Another area of HCI where corpus analysis would be useful is in the design of human-computer dialogue systems in the broad sense (i.e., including hypertext, form filling, etc.), to ensure that these dialogues are natural, or at least  coherent and efficient. For example, it is not uncommon to see web sites asking users to go through a series of questions, some of which seem to be irrelevant to the end-result, or to occur at unnatural points in time.  These dialogues are awkward because they are far from the dialogues one would have with a human being.  A corpus study of how two people interact in similar situations may have informed the designer as to what users are likely to expect.

 

2.3 Decoupling semantics and realization

 

HCI could also benefit from the general approach taken in NLG, for example in the design of multimedia systems. NLG separates the semantic information to be expressed in a text from its linguistic realization, and attempts to characterize clearly the mapping from semantics to text.  This mapping is then done “on the fly”.  Similarly, it could be fruitful for the design of multimedia systems to represent, at the design phase, the concepts relevant to the system and their relationships in abstract ways (ways which are independent of the medium). This would help inform decisions about the medium to be used and the level of redundancy which is desirable among the various media. The separation between these two levels could be useful as a design tool (a priori) in HCI. Note that this type of separation is currently attempted in Coutaz’ recent work (Coutaz, 1998, Thevenin & Coutaz, 1999), in the context of designing interfaces for the same application but to different delivery channels/environments (e.g., palm top, PC, mobile phone, etc).   In that work, Coutaz attempts to identify attributes of the target environment that play a role in the design of an interface -- such as size of display. These attributes can then be decoupled from the representation of the task enabled by the application.

 

2.4 Exploiting theories from both language and HCI to study effective communication

 

At the theoretical level, once again, the two communities base their foundations in different theories.  Theories of language try to explain (among other phenomena) what makes a discourse (or dialogue) coherent, socially acceptable, and appropriate for the reader/listener at hand, and how various communicative functions are realized in language at the various levels of the linguistic systems (e.g., semantic, lexical and syntactic).  In HCI, the two main theories of influence are cognitive psychology, which focuses on human perceptual and problem-solving capabilities, and sociology, in its attempts to understand how people make sense of their environment (with the world and with each other). HCI has heavily borrowed and adapted methodologies from both disciplines.

 

Yet, both HCI and NLG are concerned with the effectiveness of communication, and we can see parallels between their various concerns.  HCI design practitioners are concerned with such issues as information grouping and differentiation, consistency with the ways users perform their tasks, and clear specification of the purpose of each interface element. This is analogous to ensuring in NLG that a chunk of text is coherent and achieves one or more specific communicative goals the user can recognize, and that a sequence of such chunks (or moves in a dialogue) is also coherent.

 

Although not explicitly mentioned in these terms, this view is essentially that being exploited by NLG researchers working on generating “flexible” or “adaptive” hypertext (e.g., Brusilovsky, 1996, Fink et al., 1997 and Dale et al., 1998). In these contexts, web interaction is modeled as a dialogue between the user and the computer, and what is presented in a succession of screens follows that dialogue model. It may be interesting to study the analogy further, with theories from both HCI and NLP/linguistics shedding light on the problem.

 

2.5 Addressing the evaluation problem in NLG

 

Finally, evaluation is often a problem for NLG researchers (e.g., Dale & Mellish, 1998). System evaluation is often done through evaluation of the text produced, either against characteristics of the corpus studied (e.g., Vander Linden & Martin, 1995), or against human judgement of readability and coherence as compared to corresponding human-authored texts (e.g., Coch, 1996 and Lester & Porter, 1997). But when designing a system for real use, this type of evaluation is not sufficient, and may  not even be appropriate.  There are a number of methodologies for evaluation in HCI which should be applied (and adapted) for NLG.

 

3. Where HCI and NLP meet

 

3.1 Language interfaces

 

Of course, HCI and NLP should meet in one obvious place: the natural language interface. The main paradigm in HCI design today is direct manipulation. However, natural language interfaces have several advantages over direct manipulation: they allow references to objects that are not directly visible and to events that have occurred in the past or will occur in the future (Cohen et al., 1994). In addition, with the increasing number of small displays (e.g., mobile phones) and mobile devices, vocal interaction between user and on-line services will probably become more prominent.  This is an obvious instance where  NLG and HCI experts should collaborate.   

 

Speech interfaces are not the only point of contact between HCI and NLG, though. Another type of interface where the two disciplines meet is one in which documents act as interface.  This is the case, for example, for web pages, or any form of hypertext.  There, interaction occurs within the document/text. While issues related to language and dialogue are important here, so are other interactional issues. An example of these issues is the trade-off between the number of hypertext links the user must traverse to arrive at the appropriate information and the amount of text to be presented at each point.  Another example concerns the positioning of new windows and whether the old window disappears or not.  A third example concerns the way a hypertext anchor is specified, and if and how information about the target page should be provided.  These issues relate to the interface proper, and the interaction between the user and the computer.

 

3.2. Computer Supporter Collaborative Work (CSCW) or GroupWare

 

CSCW or GroupWare systems address computer-mediated human communication. The design of these systems can benefit from the extensive studies in NLG, and more specifically: (1) from typologies of communicative intentions; (2) from existing templates for specific types of messages; and (3) from the way formal relationships among the communication partners affect the communication format and language.  In addition, NLG studies can inform the design of CSCW systems which propose guidance to users as to message structure, tone, and phrasing.

 

3.3 Exploiting the output of HCI as the input for NLG

 

An important problem in NLG is obtaining and representing in the system the knowledge required producing texts. This includes the knowledge from which texts are generated (i.e., the information underlying the texts) and linguistic knowledge required to produce the texts.  In some cases, information produced by HCI researchers (or practitioners) can be exploited in this way for NLG systems.  For example, task models can be exploited to generate documentation and on-line help (e.g., Paris et al., 1998): they can provide both the information to be included in the texts, and guide the structure of the texts to be generated.  Another example (although not explicitly presented as exploiting an HCI artifact) can be found in (Grosz & Sidner, 1986), where the structure of the dialogue rests on simple task descriptions.  An interesting research direction might be to explore whether sophisticated task formalisms which have been generated by the HCI community (e.g.,  task formalisms which can represent complex task hierarchies, with relationships such as boolean operations, strict and loose precedence, iteration, etc.) can support other type of dialogues.  These are two examples of models and tools used by one community that can be exploited by the other.

 

4. Some examples of the cross-fertilization as experienced in specific projects

 

We will briefly review in this section two projects in which we have been involved, and show how our joint HCI and NLG expertise benefit them.

 

4.1 The Isolde Project

 

The Isolde[1] project is concerned with the design and development of a tool to support the production of hypertext-based on-line help for software systems, using language technology  (Paris et al., 1998).  The project’s emphasis was to try to address some of the limitations of current language technology that prevent its use in realistic settings. In particular, our concern was with the knowledge acquisition issue: how to obtain the knowledge required for the generation of on-line help. While the project started as an NLG project, we quickly found that both our HCI and NLG expertise were required if we wanted to design and develop a realistic system:

(1)   We needed to find a representation for the information from which the text was to be generated. We analysed a corpus of on-line help, and observed that the part of the documentation that may be generated automatically would be the procedural on-line help.  It is only for this aspect of the documentation that it may be possible to obtain the information underlying the text.  We further noted that task models like the ones produced by HCI experts during system design would provide much of that information.  This step required both our NLG and HCI  expertise. 

(2)   We studied the task of the prospective system’s end users (the technical writers) to understand better the place of a system like the one we were proposing to develop.  This was crucial to understand the scope of the system’s functionality, the potential sources of its input, etc.  This was performed doing a user requirements analysis and a task analysis, requiring our HCI expertise.

(3)   Once again working with the potential end users, we designed the possible interface for creating and manipulating the task models that would provide the input to the NLG module. We also ensured the readability and usability of the formalism chosen to represent the task models. This required HCI expertise.

(4)   We studied the output required of our system, including the nature of the hypertext required.  We used methodologies from both  NLP and HCI  here.  We would like to be able to answer several questions:   Can we get criteria for good on-line help, good documentation, and good hypertext-based help? Can we characterize the differences between manuals and on-line help? Can we characterize how hypertext is best presented? (As mentioned before, we believe there are some interaction issues not related only to language, and these issues are often ignored, at least in NLG systems.). We believe our joint expertise is required to answer these questions. 

(5)   If the resulting system is to be realistic, the end-users need to be able to augment or change its linguistic resources. We thus need to understand (1) which aspect of the linguistic resources could be tuned (NLG expertise), and  (2) how is the user to interact with them (HCI expertise).

(6)   Finally, we need to evaluate the system. This should not be an evaluation of only the generated on-line help, but also of the usability of the system as a whole (HCI and NLG expertise).

 

 

4.2 Tailored Delivery on the Web

 

We are also involved in a new internal project concerned with the tailored delivery of information on the web. This project’s emphasis is to combine information retrieval, language technology and user modeling techniques for tailored delivery.  Once again, we find that our HCI expertise complements our language expertise, in two specific areas:

(1)   In the design of the interface, and, in particular, in the user interaction required to build the user model that supports tailored delivery.

(2)   In the design of the system, as we want to ensure the system can produce a tailored presentation onto a variety of medium (e.g., written text, web-based hypertext, display on a palm pilot, etc.). We are applying both our expertise to study how to represent the constraints of the delivery medium and provide a mapping between the information to be presented and the medium.

 

 

5. Conclusions

 

We believe strongly that the HCI and NLP communities should work together on a wide variety of problems. We have outlined above where we think cross-fertilization can occur, and why the combination of the two types of expertise could be beneficial. We have also presented some specific examples from projects in which we are involved, pointing out where it has been necessary to apply our joint expertise.

 

Bibliography

Brusilovsky P. (1996) Methods and techniques of adaptive hypermedia.  User Modeling and User Adapted Interaction, 6(2-3).

 

Coch, J. (1996). Evaluating and comparing three text production techniques. In Proceedings of the Sixteen International Conference on Computational Linguistics (COLING’96).

 

Cohen, P. R., Oviatt, S. L. The Role of Voice in Human-Machine Communication. In Voice Communication Between Humans and Machines, pp. 34-75, National Academy Press, 1994.

Coutaz, J. Portability of User Interfaces: “Writing it once” is not enough. Invited talk at HCI 98, Sheffield, UK.

 

Dale, R. & Mellish, C. (1998). Towards evaluation in natural language generation. In Proceedings of the First International Conference on Language Resources and Evaluation, Granada, Spain.

 

Dale, R. Oberlander, J., Milosavljevic, M. & Knott, A. (1998)  Integrating Natural Language Generation and Hypertext to Produce Dynamic Documents.  Interacting with Computers, 11 (2), December.

 

Fink J., Kobsa A. A. & Schreck J. (1997) Personalised Hypermedia Information through Adaptive and Adaptable System Features: User Modeling, Privacy and Security Issues.  In Mullery A., Besson M., Campolargo R. and Reed R (eds), Intelligence in Services and Networks: Technology for Cooperative Competition.  Pages 459-467.  Berlin Heidelberg: Springer.

 

Grosz, B. & Sidner, C. (1986). Attention, intention and the structure of discourse. Computational Linguistics, 12:175-206.

 

Lester, J. & Porter, B. (1997).  Developing and empirically evaluating robust explanation generators: The KNIGHT experiments. Computational Linguistics, 23 (1): 65-101.

 

Thevenin, D. & Coutaz, J. (1999) Presentations for Mobile Users Adaptation and Plasticity of User Interfaces. Presented to i3-spring99  Workshop on Adaptive Design of Interactive Multimedia.

 

Vander Linden K & Martin, J. (1995). Expressing rhetorical relations in instructional texts: A case study of the purpose relation. Computational Linguistics, 21 (1): 29-57.



[1] Isolde stands for an Integrated Software and On-Line Documentation Environment. The Isolde project is partially supported by the Office of Naval Research ONR) – Grant N00014096-1-0465.