ACL 2014 Workshop on Semantic Parsing (SP14)

Room: Salon VI (a.k.a Grand VI)
June 26, 2014
Baltimore, MD

Semantic parsers map sentences to formal representations of their underlying meaning. Recently, algorithms have been developed to learn to recover increasingly expressive representations with ever weaker forms of supervision. These advances have enabled many applications, including question answering, relation extraction, robot control, interpreting instructions, and generating programs.

This workshop, collocated with ACL 2014, aims to achieve two goals. First, to bring together researchers in the field to discuss the state of the art and opportunities for future research. Second, to create a stage for presenting the variety of current approaches, thereby providing a unique opportunity for new entrants to the field.

We would like to thank the speakers, presenters and attendees for making SP14 such a success. Thank you!

Invited Speakers

Kevin Knight (University of Southern California / Information Sciences Institute)
Percy Liang (Stanford University)
Raymond Mooney (The University of Texas Austin)
Hoifung Poon (Microsoft Research)
Mark Steedman (The University of Edinburgh)
Stefanie Tellex (Brown University)

Program

ShowHide all abstracts

9:00	Opening
9:05	Opening invited talk Semantic Parsing: Past, Present, and Future SLIDES Raymond Mooney I first review the long history of semantic parsing from its roots in logic, to manually developed parsers, and finally to machine learning approaches. I then survey recent work, focusing on the issues of reducing supervision, scaling to broader coverage, and grounding in perception and action. Finally, I discuss what I believe is an important issue for future research: integrating distributional and logical approaches to semantics.
9:50	Invited talk Can a Machine Translate Without Knowing What Translation Is? Kevin Knight This talk will address the possibility of statistical semantics-based machine translation. What components are necessary? How can they be wired together? How can we best capture (describe) the required linguistic transformations? What data is needed to train the components?
10:20	Exceptional submission talk Low-dimensional Embeddings of Logic PDF SLIDES Tim Rocktäschel, Matko Bošnjak, Sameer Singh and Sebastian Riedel Many machine reading approaches, from shallow information extraction to deep semantic parsing, map natural language to symbolic representations of meaning. Representations such as first-order logic capture the richness of natural language and support complex reasoning, but often fail in practice due to their reliance on logical background knowledge and the difficulty of scaling up inference. In contrast, low-dimensional embeddings (i.e. distri- butional representations) are efficient and enable generalization, but it is unclear how reasoning with embeddings could support the full power of symbolic representations such as first-order logic. In this proof-of-concept paper we address this by learning embeddings that simulate the behavior of first-order logic.
10:30	Coffee break
11:00	Exceptional submission talk Combining Formal and Distributional Models of Temporal and Intensional Semantics PDF SLIDES Mike Lewis and Mark Steedman We outline a vision for computational semantics in which formal compositional semantics is combined with a powerful, structured lexical semantics derived from distributional statistics. We consider how existing work (Lewis and Steedman, 2013) could be extended with a much richer lexical semantics using recent techniques for modelling processes (Scaria et al., 2013) - for example, learning that visiting events start with arriving and end with leaving. We show how to closely integrate this information with theories of formal semantics, allowing complex compositional inferences such as is visiting -> has arrived in but will leave, which requires interpreting both the function and content words. This will allow machine reading systems to understand not just what has happened, but when.
11:10	Exceptional submission talk Cooking with Semantics PDF SLIDES Jonathan Malmaud, Earl Wagner, Nancy Chang and Kevin Murphy We are interested in the automatic interpretation of how-to instructions, such as cooking recipes, into semantic representations that can facilitate sophisticated question answering. Recent work has shown impressive results on semantic parsing of instructions with minimal supervision, but such techniques cannot handle much of the situated and ambiguous language used in instructions found on the web. In this paper, we suggest how to extend such methods using a model of pragmatics, based on a rich representation of world state.
11:20	Poster session
12:30	Lunch break
2:10	Invited talk Semantic Parsing for Cancer Panomics SLIDES Hoifung Poon Advances in sequencing technology have made available a plethora of panomics data for cancer research, yet the search for disease genes and drug targets remains a formidable challenge. Biological knowledge such as pathways can play an important role by constraining the search space and boosting the signal-to-noise ratio. The majority of knowledge resides in text (e.g., journal publications), which has been undergoing its own exponential growth, making it mandatory to develop machine reading methods for automatic knowledge extraction. In this talk, I will formulate the machine reading task for pathway extraction as a semantic parsing problem, review the state of the art and open challenges, and present our Literome project and latest attack to the problem using grounded unsupervised semantic parsing.
2:50	Invited talk Robust Semantics for Semantic Parsers SLIDES Mark Steedman Semantic parsing---that is, is the automatic induction of parsers that build meaning representations by being trained on paired sentences and meanings, the way that a child learns their native language---is potentially a very powerful mechanism for natural language processing. For example, if we had the same access to the universal conceptual language as the child, we could in principle train parser-generators for interlingual machine translation using it, possibly with greater efficiency than synchronous grammars trained on parallel text. The fact that we do not have access to such meaning representations is merely symptomatic of a much more serious shortage of training datasets for semantic parser induction. In fact there are almost no large datasets of this kind. As a result, there has been a search for proxies for string-meaning representation datasets, such as question-answer pairs and large knowledge structures such as FreeBase. This talk will examine a number of distributional and nondistributional semantic representations that can be used to mediate semantic parsing more directly at the scale of FreeBase queries and Text Entailment tasks. It draws on joint work with Mike Lewis, Siva Reddy, and Mirella Lapata.
3:30	Coffee break
4:00	Invited talk Asking for Help Using Inverse Semantics SLIDES Stefanie Tellex Robots inevitably fail, often without the ability to recover autonomously. We demonstrate an approach for enabling a robot to recover from failures by communicating its need for specific help to a human partner using natural language. Our approach automatically detects failures, then generates targeted spoken-language requests for help such as ``Please give me the white table leg that is on the black table.'' Once the human partner has repaired the failure condition, the system resumes full autonomy. We present a novel inverse semantics algorithm for generating effective help requests. In contrast to forward semantic models that interpret natural language in terms of robot actions and perception, our inverse semantics algorithm generates requests by emulating the human's ability to interpret a request using the Generalized Grounding Graph framework. To assess the effectiveness of our approach, we present a corpus-based online evaluation, as well as an end-to-end user study, demonstrating that our approach increases the effectiveness of human interventions compared to static requests for help.
4:40	Invited talk Computing with Natural Language SLIDES Percy Liang Today, the tremendous growth of semi-structured data far outpaces our ability to ask interesting deep questions of it. Moreover, much of the advanced data processing and analysis is limited to the privileged few who have programming expertise. In this talk, I will entertain the possibility of using natural language as a universal and agile interface for querying, and more generally computing with, data. Specifically, I will discuss two recent projects: (i) learning to map natural language questions into database queries on Freebase; and (ii) learning to map natural language queries onto XPath expressions that extract entities from web pages. In both these projects, I will discuss the statistical and computational challenges of learning from weakly-supervised data.
5:20	Closing

Accepted Submissions

Learning a Lexicon for Broad-coverage Semantic Parsing James Allen Semantic Parsing Using Distributional Semantics and Probabilistic Logic Islam Beltagy, Katrin Erk and Raymond Mooney Large-scale CCG Induction from the Groningen Meaning Bank Sebastian Beschke, Yang Liu and Wolfgang Menzel Semantic Parsing for Text to 3D Scene Generation Angel Chang, Manolis Savva and Chris Manning Leveraging Frame Semantics and Distributional Semantics for Unsupervised Semantic Slot Induction in Spoken Dialogue Systems Yun-nung Chen, William Yang Wang and Alexander Rudnicky Semantic Parsing for Information Extraction Eunsol Choi, Tom Kwiatkowski and Luke Zettlemoyer Parsing and Grounding Referring Expressions in Automatically Constructed 3D Models Nicholas FitzGerald and Luke Zettlemoyer Graph-based Algorithms for Semantic Parsing Jeffrey Flanigan, Samuel Thomson, David Bamman, Jesse Dodge, Manaal Faruqui, Brendan O'Connor, Nathan Schneider, Swabha Swayamdipta, Chris Dyer and Noah A. Smith [Related ACL 2014 publication] A Deep Architecture for Semantic Parsing Edward Grefenstette, Phil Blunsom, Nando De Freitas and Karl Moritz Hermann Symmetry-based Semantic Parsing Chloé Kiddon and Pedro Domingos Leveraging Heterogeneous Data Sources for Relational Semantic Parsing Meghana Kshirsagar, Nathan Schneider and Chris Dyer Context-dependent Semantic Parsing for Time Expressions Kenton Lee, Yoav Artzi, Jesse Dodge and Luke Zettlemoyer [Related ACL 2014 publication] Combining Formal and Distributional Models of Temporal and Intensional Semantics Exceptional Submission Award Mike Lewis and Mark Steedman Cooking with Semantics Exceptional Submission Award Jonathan Malmaud, Earl Wagner, Nancy Chang and Kevin Murphy Representing Caused Motion in Embodied Construction Grammar Ellen K Dodge and Miriam R L Petruck Constructing Semantic Parsing Datasets from Technical Documentation Kyle Richardson and Jonas Kuhn Notes on the MCTest Dataset for the Open-domain Machine Comprehension of Text Matthew Richardson, Christopher J.C. Burges and Erin Renshaw [Related EMNLP 2013 publication] Low-dimensional Embeddings of Logic Exceptional Submission Award Tim Rocktäschel, Matko Bošnjak, Sameer Singh and Sebastian Riedel Software Requirements: A New Domain For Semantic Parsers Michael Roth, Themistoklis Diamantopoulos, Ewan Klein and Andreas Symeonidis From Treebank Parses To Episodic Logic and Commonsense Inference Lenhart Schubert On Maximum Spanning DAG Algorithms for Semantic DAG Parsing Natalie Schluter Intermediary Semantic Representation Through Proposition Structures Gabriel Stanovsky, Jessica Ficler, Ido Dagan and Yoav Goldberg Efficient Logical Inference for Semantic Processing Ran Tian, Yusuke Miyao and Takuya Matsuzaki A New Corpus for Context-dependent Semantic Parsing Andreas Vlachos and Stephen Clark Towards README-EVAL : Interpreting Readme File Instructions James White Freebase QA: Information Extraction or Semantic Parsing? Xuchen Yao, Jonathan Berant and Benjamin Van Durme

Announcements

25 March 2014: Submission deadline extended to ~~April 4, 11:59pm (GMT-12:00)~~
18 November 2013: First call for submissions is out

Call for Submissions

Submissions are encouraged to discuss visionary and adventurous research directions. Three exceptional submissions will be awarded Google Exceptional Submission Awards. All accepted submissions will be presented as posters. Additionally, a small number of selected submissions will be presented orally.

We seek submissions of 2-4 page (excluding references) abstracts on semantic parsing. Topics of interest include, but not limited to:

Situated language understanding in interactive systems, such as question answering, robot control and interpreting instructions.
Algorithms for learning semantic parsers.
Efficient inference for semantic parsing.
Using compositional distributional semantic representations and methods for semantic parsing.
Logical representations of language and their use in learned systems.
Semantic parsing for information extraction.
Using semantic parsers for other NLP tasks, such as machine translation, co-reference resolution and summarization.
Using semantic parsing methods and representations for language generation.
Novel domains and resources for training and evaluating semantic parsers.
Using tools, such as morphology analyzers and taggers, to improve semantic parsing.

Each submission must be anonymized and contain a title and abstract text. Abstracts on work published or submitted elsewhere are welcome. Please submit your papers at https://www.softconf.com/acl2014/SP14/.

To encourage inclusiveness and the presentation of speculative and recent work, inclusion in the conference proceedings is optional. The author's preference should be indicated with the final submission.

Important Dates

~~4 April 2014 (11:59pm, GMT-12:00): Abstracts due~~
~~18 April 2014: Reviews due~~
~~21 April 2014: Notification of acceptance~~
~~28 April 2014: Camera-ready and final abstracts due~~
~~26 June 2014: Workshop date~~

Organizers

Yoav Artzi (University of Washington)
Tom Kwiatkowski (Allen Institute for AI)
Jonathan Berant (Stanford University)

Steering Committee

Percy Liang (Stanford University)
Jakob Uszkoreit (Google)
Luke Zettlemoyer (University of Washington)

Program Committee

Gabor Angeli (Stanford University)
John Blitzer (Google)
Johan Bos (University of Groningen)
Qingqing Cai (Temple University)
Stephen Clark (Cambridge University)
Dipanjan Das (Google)
Anthony Fader (University of Washington)
Nicholas FitzGerald (University of Washington)
Dan Goldwasser (University of Maryland)
Karl Moritz Hermann (University of Oxford)
Chloe Kiddon (University of Washington)
Jayant Krishnamurthy (Carnegie Mellon University)
Nate Kushman (Massachusetts Institute of Technology)
Mike Lewis (The University of Edinburgh)
Smaranda Muresan (Columbia University)
Hoifung Poon (Microsoft Research)
Siva Reddy (The University of Edinburgh)
Matthew Richardson (Microsoft Research)
Dan Roth (University of Illinois Urbana-Champaign)
Andreas Vlachos (University of Cambridge)
Alexander Yates (Temple University)
Mark Yatskar (University of Washington)

Sponsored by