Rashmi Prasad


2021

pdf bib
DialogActs based Search and Retrieval for Response Generation in Conversation Systems
Nidhi Arora | Rashmi Prasad | Srinivas Bangalore
Proceedings of the 18th International Conference on Natural Language Processing (ICON)

Designing robust conversation systems with great customer experience requires a team of design experts to think of all probable ways a customer can interact with the system and then author responses for each use case individually. The responses are authored from scratch for each new client and application even though similar responses have been created in the past. This happens largely because the responses are encoded using domain specific set of intents and entities. In this paper, we present preliminary work to define a dialog act schema to merge and map responses from different domains and applications using a consistent domain-independent representation. These representations are stored and maintained using an Elasticsearch system to facilitate generation of responses through a search and retrieval process. We experimented generating different surface realizations for a response given a desired information state of the dialog.

pdf bib
Intent Features for Rich Natural Language Understanding
Brian Lester | Sagnik Ray Choudhury | Rashmi Prasad | Srinivas Bangalore
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers

Complex natural language understanding modules in dialog systems have a richer understanding of user utterances, and thus are critical in providing a better user experience. However, these models are often created from scratch, for specific clients and use cases and require the annotation of large datasets. This encourages the sharing of annotated data across multiple clients. To facilitate this we introduce the idea of intent features: domain and topic agnostic properties of intents that can be learnt from the syntactic cues only, and hence can be shared. We introduce a new neural network architecture, the Global-Local model, that shows significant improvement over strong baselines for identifying these features in a deployed, multi-intent natural language understanding module, and more generally in a classification setting where a part of an utterance has to be classified utilizing the whole context.

2019

pdf bib
Ambiguity in Explicit Discourse Connectives
Bonnie Webber | Rashmi Prasad | Alan Lee
Proceedings of the 13th International Conference on Computational Semantics - Long Papers

Discourse connectives are known to be subject to both usage and sense ambiguity, as has already been discussed in the literature. But discourse connectives are no different from other linguistic expressions in being subject to other types of ambiguity as well. Four are illustrated and discussed here.

2018

pdf bib
Discourse Annotation in the PDTB: The Next Generation
Rashmi Prasad | Bonnie Webber | Alan Lee
Proceedings of the 14th Joint ACL-ISO Workshop on Interoperable Semantic Annotation

2017

pdf bib
Towards Full Text Shallow Discourse Relation Annotation: Experiments with Cross-Paragraph Implicit Relations in the PDTB
Rashmi Prasad | Katherine Forbes Riley | Alan Lee
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

Full text discourse parsing relies on texts comprehensively annotated with discourse relations. To this end, we address a significant gap in the inter-sentential discourse relations annotated in the Penn Discourse Treebank (PDTB), namely the class of cross-paragraph implicit relations, which account for 30% of inter-sentential relations in the corpus. We present our annotation study to explore the incidence rate of adjacent vs. non-adjacent implicit relations in cross-paragraph contexts, and the relative degree of difficulty in annotating them. Our experiments show a high incidence of non-adjacent relations that are difficult to annotate reliably, suggesting the practicality of backing off from their annotation to reduce noise for corpus-based studies. Our resulting guidelines follow the PDTB adjacency constraint for implicits while employing an underspecified representation of non-adjacent implicits, and yield 62% inter-annotator agreement on this task.

2016

pdf bib
A Discourse-Annotated Corpus of Conjoined VPs
Bonnie Webber | Rashmi Prasad | Alan Lee | Aravind Joshi
Proceedings of the 10th Linguistic Annotation Workshop held in conjunction with ACL 2016 (LAW-X 2016)

pdf bib
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Yuji Matsumoto | Rashmi Prasad
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

pdf bib
Annotating Discourse Relations with the PDTB Annotator
Alan Lee | Rashmi Prasad | Bonnie Webber | Aravind K. Joshi
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

The PDTB Annotator is a tool for annotating and adjudicating discourse relations based on the annotation framework of the Penn Discourse TreeBank (PDTB). This demo describes the benefits of using the PDTB Annotator, gives an overview of the PDTB Framework and discusses the tool’s features, setup requirements and how it can also be used for adjudication.

2015

pdf bib
The CoNLL-2015 Shared Task on Shallow Discourse Parsing
Nianwen Xue | Hwee Tou Ng | Sameer Pradhan | Rashmi Prasad | Christopher Bryant | Attapol Rutherford
Proceedings of the Nineteenth Conference on Computational Natural Language Learning - Shared Task

pdf bib
Semantic Relations in Discourse: The Current State of ISO 24617-8
Rashmi Prasad | Harry Bunt
Proceedings of the 11th Joint ACL-ISO Workshop on Interoperable Semantic Annotation (ISA-11)

pdf bib
Bridging Sentential and Discourse-level Semantics through Clausal Adjuncts
Rashmi Prasad | Bonnie Webber | Alan Lee | Sameer Pradhan | Aravind Joshi
Proceedings of the First Workshop on Linking Computational Models of Lexical, Sentential and Discourse-level Semantics

2014

pdf bib
Reflections on the Penn Discourse TreeBank, Comparable Corpora, and Complementary Annotation
Rashmi Prasad | Bonnie Webber | Aravind Joshi
Computational Linguistics, Volume 40, Issue 4 - December 2014

2013

pdf bib
UWM-TRIADS: Classifying Drug-Drug Interactions with Two-Stage SVM and Post-Processing
Majid Rastegar-Mojarad | Richard D. Boyce | Rashmi Prasad
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)

2012

pdf bib
Evaluation of Discourse Relation Annotation in the Hindi Discourse Relation Bank
Sudheer Kolachina | Rashmi Prasad | Dipti Misra Sharma | Aravind Joshi
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

We describe our experiments on evaluating recently proposed modifications to the discourse relation annotation scheme of the Penn Discourse Treebank (PDTB), in the context of annotating discourse relations in Hindi Discourse Relation Bank (HDRB). While the proposed modifications were driven by the desire to introduce greater conceptual clarity in the PDTB scheme and to facilitate better annotation quality, our findings indicate that overall, some of the changes render the annotation task much more difficult for the annotators, as also reflected in lower inter-annotator agreement for the relevant sub-tasks. Our study emphasizes the importance of best practices in annotation task design and guidelines, given that a major goal of an annotation effort should be to achieve maximally high agreement between annotators. Based on our study, we suggest modifications to the current version of the HDRB, to be incorporated in our future annotation work.

2010

pdf bib
Using entity features to classify implicit discourse relations
Annie Louis | Aravind Joshi | Rashmi Prasad | Ani Nenkova
Proceedings of the SIGDIAL 2010 Conference

pdf bib
Realization of Discourse Relations by Other Means: Alternative Lexicalizations
Rashmi Prasad | Aravind Joshi | Bonnie Webber
Coling 2010: Posters

pdf bib
Annotation of Discourse Relations for Conversational Spoken Dialogs
Sara Tonelli | Giuseppe Riccardi | Rashmi Prasad | Aravind Joshi
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

In this paper, we make a qualitative and quantitative analysis of discourse relations within the LUNA conversational spoken dialog corpus. In particular, we first describe the Penn Discourse Treebank (PDTB) and then we detail the adaptation of its annotation scheme to the LUNA corpus of Italian task-oriented dialogs in the domain of software/hardware assistance. We discuss similarities and differences between our approach and the PDTB paradigm and point out the peculiarities of spontaneous dialogs w.r.t. written text, which motivated some changes in the annotation strategy. In particular, we introduced the annotation of relations between non-contiguous arguments and we modified the sense hierarchy in order to take into account the important role of pragmatics in dialogs. In the final part of the paper, we present a comparison between the sense and connective frequency in a representative subset of the LUNA corpus and in the PDTB. Such analysis confirmed the differences between the two corpora and corroborates our choice to introduce dialog-specific adaptations.

pdf bib
Exploiting Scope for Shallow Discourse Parsing
Rashmi Prasad | Aravind Joshi | Bonnie Webber
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

We present an approach to automatically identifying the arguments of discourse connectives based on data from the Penn Discourse Treebank. Of the two arguments of connectives, called Arg1 and Arg2, we focus on Arg1, which has proven more challenging to identify. Our approach employs a sentence-based representation of arguments, and distinguishes ""intra-sentential connectives"", which take both their arguments in the same sentence, from ""inter-sentential connectives"", whose arguments are found in different sentences. The latter are further distinguished by paragraph position into ""ParaInit"" connectives, which appear in a paragraph-initial sentence, and ""ParaNonInit"" connectives, which appear elsewhere. The paper focusses on predicting Arg1 of Inter-sentential ParaNonInit connectives, presenting a set of scope-based filters that reduce the search space for Arg1 from all the previous sentences in the paragraph to a subset of them. For cases where these filters do not uniquely identify Arg1, coreference-based heuristics are employed. Our analysis shows an absolute 3% performance improvement over the high baseline of 83.3% for identifying Arg1 of Inter-sentential ParaNonInit connectives.

2009

pdf bib
The Hindi Discourse Relation Bank
Umangi Oza | Rashmi Prasad | Sudheer Kolachina | Dipti Misra Sharma | Aravind Joshi
Proceedings of the Third Linguistic Annotation Workshop (LAW III)

2008

pdf bib
A Pilot Annotation to Investigate Discourse Connectivity in Biomedical Text
Hong Yu | Nadya Frid | Susan McRoy | Rashmi Prasad | Alan Lee | Aravind Joshi
Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing

pdf bib
Towards an Annotated Corpus of Discourse Relations in Hindi
Rashmi Prasad | Samar Husain | Dipti Sharma | Aravind Joshi
Proceedings of the 6th Workshop on Asian Language Resources

pdf bib
The Penn Discourse TreeBank 2.0.
Rashmi Prasad | Nikhil Dinesh | Alan Lee | Eleni Miltsakaki | Livio Robaldo | Aravind Joshi | Bonnie Webber
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)

We present the second version of the Penn Discourse Treebank, PDTB-2.0, describing its lexically-grounded annotations of discourse relations and their two abstract object arguments over the 1 million word Wall Street Journal corpus. We describe all aspects of the annotation, including (a) the argument structure of discourse relations, (b) the sense annotation of the relations, and (c) the attribution of discourse relations and each of their arguments. We list the differences between PDTB-1.0 and PDTB-2.0. We present representative statistics for several aspects of the annotation in the corpus.

2006

pdf bib
Attribution and its annotation in the Penn Discourse TreeBank
Rashmi Prasad | Nikhil Dinesh | Alan Lee | Aravind Joshi | Bonnie Webber
Traitement Automatique des Langues, Volume 47, Numéro 2 : Discours et document : traitements automatiques [Computational Approaches to Discourse and Document Processing]

pdf bib
Learning to Generate Naturalistic Utterances Using Reviews in Spoken Dialogue Systems
Ryuichiro Higashinaka | Rashmi Prasad | Marilyn A. Walker
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

pdf bib
Annotating Attribution in the Penn Discourse TreeBank
Rashmi Prasad | Nikhil Dinesh | Alan Lee | Aravind Joshi | Bonnie Webber
Proceedings of the Workshop on Sentiment and Subjectivity in Text

2005

pdf bib
Attribution and the (Non-)Alignment of Syntactic and Discourse Arguments of Connectives
Nikhil Dinesh | Alan Lee | Eleni Miltsakaki | Rashmi Prasad | Aravind Joshi | Bonnie Webber
Proceedings of the Workshop on Frontiers in Corpus Annotations II: Pie in the Sky

2004

pdf bib
Trainable Sentence Planning for Complex Information Presentations in Spoken Dialog Systems
Amanda Stent | Rashmi Prasad | Marilyn Walker
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

pdf bib
Annotation and Data Mining of the Penn Discourse TreeBank
Rashmi Prasad | Eleni Miltsakaki | Aravind Joshi | Bonnie Webber
Proceedings of the Workshop on Discourse Annotation

pdf bib
Annotating Discourse Connectives and Their Arguments
Eleni Miltsakaki | Aravind Joshi | Rashmi Prasad | Bonnie Webber
Proceedings of the Workshop Frontiers in Corpus Annotation at HLT-NAACL 2004

pdf bib
The Penn Discourse Treebank
Eleni Miltsakaki | Rashmi Prasad | Aravind Joshi | Bonnie Webber
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)

2002

pdf bib
Training a Dialogue Act Tagger for Human-human and Human-computer Travel dialogues
Rashmi Prasad | Marilyn Walker
Proceedings of the Third SIGdial Workshop on Discourse and Dialogue

pdf bib
What’s the Trouble: Automatically Identifying Problematic Dialogues in DARPA Communicator Dialogue Systems
Helen Wright Hastie | Rashmi Prasad | Marilyn Walker
Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics

pdf bib
Automatic Evaluation: Using a DATE Dialogue Act Tagger for User Satisfaction and Task Completion Prediction
Helen Wright Hastie | Rashmi Prasad | Marilyn Walker
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC’02)