Philip R. Cohen

Also published as: Phil R. Cohen, Philip Cohen


2024

pdf bib
Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach
Zhuang Li | Levon Haroutunian | Raj Tumuluri | Philip Cohen | Reza Haf
Findings of the Association for Computational Linguistics: EACL 2024

Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3.5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive. However, relying solely on smaller language models for post-editing can limit the LLMs’ ability to generalize across domains. Moreover, the editing strategies in these methods are not optimally designed for text generation tasks. To address these limitations, we propose a neural programmer-interpreter approach that preserves the domain generalization ability of LLMs while editing their output. The editing actions in this framework are specifically devised for text generation. Extensive experiments demonstrate that the programmer-interpreter significantly enhances GPT-3.5’s performance in logical form-to-text conversion and low-resource machine translation, surpassing other state-of-the-art (SOTA) LLM post-editing methods in cross-domain settings.

2023

pdf bib
Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models
Levon Haroutunian | Zhuang Li | Lucian Galescu | Philip Cohen | Raj Tumuluri | Gholamreza Haffari
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning
Zhuang Li | Lizhen Qu | Philip Cohen | Raj Tumuluri | Gholamreza Haffari
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem. Prior works propose to utilize the translations by either humans or machines to alleviate such issues. However, human translations are expensive, while machine translations are cheap but prone to error and bias. In this work, we propose an active learning approach that exploits the strengths of both human and machine translations by iteratively adding small batches of human translations into the machine-translated training set. Besides, we propose novel aggregated acquisition criteria that help our active learning method select utterances to be manually translated. Our experiments demonstrate that an ideal utterance selection can significantly reduce the error and bias in the translated data, resulting in higher parser accuracies than the parsers merely trained on the machine-translated data.

2019

pdf bib
Foundations of Collaborative Task-Oriented Dialogue: What’s in a Slot?
Philip Cohen
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

In this paper, we examine the foundations of task-oriented dialogues, in which systems are requested to perform tasks for humans. We argue that the way this dialogue task has been framed has limited its applicability to processing simple requests with atomic “slot-fillers”. However, real task-oriented dialogues can contain more complex utterances that provide non-atomic constraints on slot values. For example, in response to the system’s question “What time do you want me to reserve the restaurant?”, a user should be able to say “the earliest time available,” which cannot be handled by classic “intent + slots” approaches that do not incorporate expressive logical form meaning representations. Furthermore, situations for which it would be desirable to build task-oriented dialogue systems, e.g., to engage in mixed-initiative, collaborative or multiparty dialogues, will require a more general approach. In order to overcome these limitations and to provide such an approach, we give a logical analysis of the “intent+slot” dialogue setting using a modal logic of intention and including a more expansive notion of “dialogue state”. Finally, we briefly discuss our program of research to build a next generation of plan-based dialogue systems that goes beyond “intent + slots”.

2018

pdf bib
Active learning for deep semantic parsing
Long Duong | Hadi Afshar | Dominique Estival | Glen Pink | Philip Cohen | Mark Johnson
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Semantic parsing requires training data that is expensive and slow to collect. We apply active learning to both traditional and “overnight” data collection approaches. We show that it is possible to obtain good training hyperparameters from seed data which is only a small fraction of the full dataset. We show that uncertainty sampling based on least confidence score is competitive in traditional data collection but not applicable for overnight collection. We propose several active learning strategies for overnight data collection and show that different example selection strategies per domain perform best.

2017

pdf bib
Multilingual Semantic Parsing And Code-Switching
Long Duong | Hadi Afshar | Dominique Estival | Glen Pink | Philip Cohen | Mark Johnson
Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)

Extending semantic parsing systems to new domains and languages is a highly expensive, time-consuming process, so making effective use of existing resources is critical. In this paper, we describe a transfer learning method using crosslingual word embeddings in a sequence-to-sequence model. On the NLmaps corpus, our approach achieves state-of-the-art accuracy of 85.7% for English. Most importantly, we observed a consistent improvement for German compared with several baseline domain adaptation techniques. As a by-product of this approach, our models that are trained on a combination of English and German utterances perform reasonably well on code-switching utterances which contain a mixture of English and German, even though the training data does not contain any such. As far as we know, this is the first study of code-switching in semantic parsing. We manually constructed the set of code-switching test utterances for the NLmaps corpus and achieve 78.3% accuracy on this dataset.

2000

pdf bib
The Efficiency of Multimodal Interaction for a Map-based Task
Philip Cohen | David McGee | Josh Clow
Sixth Applied Natural Language Processing Conference

1998

pdf bib
Confirmation in Multimodal Systems
David R. McGee | Phil R. Cohen | Sharon Oviatt
36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 2

pdf bib
Confmnation in Multimodal Systems
David R. McGee | Philip R. Cohen | Sharon Oviatt
COLING 1998 Volume 2: The 17th International Conference on Computational Linguistics

1997

pdf bib
QuickSet: Multimodal Interaction for Simulation Set-up and Control
Philip R. Cohen | Michael Johnston | David McGee | Sharon Oviatt | Jay Pittman | Ira Smith | Liang Chen | Josh Clow
Fifth Conference on Applied Natural Language Processing

pdf bib
Unification-based Multimodal Integration
Michael Johnston | Philip R. Cohen | David McGee | Sharon L. Oviatt | James A. Pittman | Ira Smith
35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics

1993

pdf bib
A Simulation-Based Research Strategy for Designing Complex NL Systems
Sharon Oviatt | Philip Cohen | Michelle Wang | Jeremy Gaston
Human Language Technology: Proceedings of a Workshop Held at Plainsboro, New Jersey, March 21-24, 1993

1990

pdf bib
Performatives in a Rationally Based Speech Act Theory
Philip R. Cohen | Hector J. Levesque
28th Annual Meeting of the Association for Computational Linguistics

1989

pdf bib
The Effects of Interaction on Spoken Discourse
Sharon L. Oviatt | Philip R. Cohen
27th Annual Meeting of the Association for Computational Linguistics

1985

pdf bib
Speech Acts and Rationality
Philip R. Cohen | Hector J. Levesque
23rd Annual Meeting of the Association for Computational Linguistics

1984

pdf bib
The Pragmatics of Referring and the Modality of Communication
Philip R. Cohen
Computational Linguistics. Formerly the American Journal of Computational Linguistics, Volume 10, Number 2, April-June 1984

pdf bib
Referring as Requesting
Philip R. Cohen
10th International Conference on Computational Linguistics and 22nd Annual Meeting of the Association for Computational Linguistics

1982

pdf bib
Dependencies of Discourse Structure on the Modality of Communication: Telephone vs. Teletype
Philip R. Cohen | Scott Fertig | Kathy Starr
20th Annual Meeting of the Association for Computational Linguistics

1980

pdf bib
Signalling the Interpretation of Indirect Speech Acts
Philip R. Cohen
18th Annual Meeting of the Association for Computational Linguistics

1978

pdf bib
Speech Acts as a Basis for Understanding Dialogue Coherence
C. Raymond Perrault | James F. Allen | Philip R. Cohen
American Journal of Computational Linguistics (December 1978)