Recent developments in NLP have led to excellent performance on various semantic tasks. However, an important question that remains open is whether such methods are actually capable of modeling how linguistic meaning is shaped and influenced by context, or if they simply learn superficial patterns that reflect only explicitly stated aspects of meaning. An interesting case in point is the interpretation and understanding of implicit or underspecified language.
More concretely, language utterances may contain empty or fuzzy elements, such as the following: units of measurement, as in "she is 30" vs. "it costs 30" (30 what?), bridges and other missing links, as in "she tried to enter the car, but the door was stuck" (the door of what?), implicit semantic roles, as in "I met her while driving" (who was driving?), and various sorts of gradable phenomena; is a "small elephant" smaller than a "big bee"? Where is the boundary between "orange" and "red"?
Implicit and underspecified phenomena have been studied in linguistics and philosophy for decades (Sag, 1976; Heim, 1982; Ballmer and Pinkal, 1983), but empirical studies in NLP are scarce and far between. The number of datasets and task proposals is however growing (Roesiger et al., 2018; Elazar and Goldberg, 2019; Ebner et al., 2020; McMahan and Stone, 2020) and recent studies have shown the difficulty of annotating and modeling implicit and underspecified phenomena (Shwartz and Dagan, 2016; Scholman and Demberg, 2017; Webber et al., 2019).
The use of implicit and underspecified terms poses serious challenges to standard natural language processing models, and they often require incorporating greater context, using symbolic inference and common-sense reasoning, or more generally, going beyond strictly lexical and compositional meaning constructs. This challenge spans all phases of the NLP model's life cycle: from collecting and annotating relevant data, through devising computational methods for modelling such phenomena, to evaluating and designing proper evaluation metrics.
Furthermore, most existing efforts in NLP are concerned with one particular problem, their benchmarks are narrow in size and scope, and no common platform or standards exist for studying effects on downstream tasks. In our opinion, interpreting implicit and underspecified language is an inherent part of natural language understanding, these elements are essential for human-like interpretation, and modeling them may be critical for downstream applications.
The goal of this workshop is to bring together theoreticians and practitioners from the entire NLP cycle, from annotation and benchmarking to modeling and applications, and to provide an umbrella for the development, discussion and standardization of the study of understanding implicit and underspecified language. We solicit papers on the following, and other, topics:
As part of the workshop, we are organizing a shared task on implicit and underspecified language. The focus of this task is on modeling the necessity of clarifications due to aspects of meaning that are implicit or underspecified in context. Specifically, the task setting follows the recent proposal of predicting revision requirements in collaboratively edited instructions (Bhat et al., 2020). The data consists of instances from wikiHowToImprove (Anthonio et al., 2020) in which a revision resolved an implicit or underspecified linguist element. The following revision types are part of the data:
Final training and development sets are available here:
Access to the test data requires registration as a participant. If you are interested in participating in the shared task, please contact Michael Roth.
Invited talk [slides] [video]
|18:00||Poster session I|
|Let's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction [paper] |
Murathan Kurfalı and Robert Östling
|Implicit Phenomena in Short-answer Scoring Data [paper]|
Marie Bexte, Andrea Horbach and Torsten Zesch
|Evaluation Guidelines to Deal with Implicit Phenomena to Assess Factuality in Data-to-Text Generation [paper]|
Roy Eisenstadt and Michael Elhadad
|UnImplicit Shared Task Report: Detecting Clarification Requirements in Instructional Text [paper]|
Michael Roth and Talita Anthonio
|Abstracts||Is Sluice Resolution really just Question Answering? |
|Decontextualization: Making Sentences Stand-Alone |
Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das and Michael Collins
|(Re)construing meaning in NLP |
Sean Trott, Tiago Timponi Torrent, Nancy Chang and Nathan Schneider
|Modelling Entity Implicature based on Systemic Functional Linguistics |
Hawre Hosseini, Mehran Mansouri and Ebrahim Bagheri
|Meaning Representation of Numeric Fused-Heads in UCCA |
Ruixiang Cui and Daniel Hershcovich
|Underspecification in Executable Instructions |
Valentina Pyatkin, Royi Lachmy and Reut Tsarfaty
|Findings||Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference |
Hai Hu, Yiwen Zhang, Yina Patterson, Yanting Li, Yixin Nie and Kyle Richardson
|19:00||Working group session I (discussion / presentation)
A. Challenges and best-practices in data collection and annotation of implicit phenomena
B. What is the range of implicit phenomena? (produce a taxonomy)
C. What are the next steps in implicit and underspecified language research?
|20:00||Poster session II|
|Improvements and Extensions on Metaphor Detection [paper]|
Weicheng Ma, Ruibo Liu, Lili Wang and Soroush Vosoughi
|Human-Model Divergence in the Handling of Vagueness [paper]|
Elias Stengel-Eskin, Jimena Guallar-Blasco and Benjamin Van Durme
|TTCB System Description to a Shared Task on Implicit and Underspecified Language 2021 [paper]|
|A Mention-Based System for Revision Requirements Detection [paper]|
Ahmed Ruby, Christian Hardmeier and Sara Stymne/
|Abstracts||Superlatives in Discourse: Explicit and Implicit Domain Restrictions for Superlatives |
Valentina Pyatkin, Ido Dagan and Reut Tsarfaty
|Transformer-based language models and complement coercion: Experimental studies |
|Large Scale Crowdsourcing of Noun-Phrase Links |
Victoria Basmov, Yanai Elazar, Yoav Goldberg and Reut Tsarfaty
|Variation in conventionally implicated content: An empirical study in English and German |
Annette Hautli-Janisz and Diego Frassinelli
|Challenges in Detecting Null Relativizers in African American Language for Sociolinguistic and Psycholinguistic Applications |
Anissa Neal, Brendan O'Connor and Lisa Green
|Incorporating Human Explanations for Robust Hate Speech Detection |
Jennifer Chen, Faisal Ladhak, Daniel Li and Noémie Elhadad
|Findings||John praised Mary because _he_? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs |
Yova Kementchedjhieva, Mark Anderson and Anders Søgaard
Invited talk [slides] [video]
|22:05||Working group session II (discussion / presentation)
D. ML-based modeling of different implicit-language phenomena/tasks
E. What are the existing and/or possible NLP tasks around implicit phenomena?
F. What would be a good shared task around implicit and underspecified language?