Search Results for author: Eduardo Blanco

Found 48 papers, 13 papers with code

Disentangling Indirect Answers to Yes-No Questions in Real Conversations

1 code implementation NAACL 2022 Krishna Sanagavarapu, Jathin Singaraju, Anusha Kakileti, Anirudh Kaza, Aaron Mathews, Helen Li, Nathan Brito, Eduardo Blanco

More importantly, our results demonstrate that existing corpora with synthetic indirect answers to yes-no questions are not beneficial when working with real conversations.

Outcome-Constrained Large Language Models for Countering Hate Speech

no code implementations25 Mar 2024 Lingzi Hong, Pengcheng Luo, Eduardo Blanco, Xiaoying Song

We first explore methods that utilize large language models (LLM) to generate counterspeech constrained by potential conversation outcomes.

Text Generation

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning

no code implementations17 Mar 2024 Javad Rafiei Asl, Prajwal Panzade, Eduardo Blanco, Daniel Takabi, Zhipeng Cai

In this paper, we introduce RobustSentEmbed, a self-supervised sentence embedding framework designed to improve both generalization and robustness in diverse text representation tasks and against a diverse set of adversarial attacks.

Contrastive Learning Semantic Textual Similarity +3

Hate Cannot Drive out Hate: Forecasting Conversation Incivility following Replies to Hate Speech

no code implementations8 Dec 2023 Xinchen Yu, Eduardo Blanco, Lingzi Hong

A linguistic analysis uncovers the differences in the language of replies that elicit follow-up conversations with high and low incivility.

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages

1 code implementation20 Oct 2023 Zijie Wang, Md Mosharaf Hossain, Shivam Mathur, Terry Cruz Melo, Kadir Bulut Ozler, Keun Hee Park, Jacob Quintero, MohammadHossein Rezaei, Shreya Nupur Shakya, Md Nayem Uddin, Eduardo Blanco

Experimental results demonstrate that monolingual fine-tuning is beneficial if training data can be obtained via distant supervision for the language of interest (5 languages).

Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference

1 code implementation11 Jul 2023 Sushma Anand Akoju, Robert Vacareanu, Haris Riaz, Eduardo Blanco, Mihai Surdeanu

To this end, we modify the original texts using a set of phrases - modifiers that correspond to universal quantifiers, existential quantifiers, negation, and other concept modifiers in Natural Logic (NL) (MacCartney, 2009).

Natural Language Inference Negation +2

Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding

1 code implementation26 Oct 2022 Md Mosharaf Hossain, Eduardo Blanco

Inspired by the fact that understanding a negated statement often requires humans to infer affirmative interpretations, in this paper we show that doing so benefits models for three natural language understanding tasks.

Natural Language Inference Natural Language Understanding +2

Written Justifications are Key to Aggregate Crowdsourced Forecasts

1 code implementation Findings (EMNLP) 2021 Saketh Kotamraju, Eduardo Blanco

Our experiments show that the majority and weighted vote baselines are competitive, and that the written justifications are beneficial to call a question throughout its life except in the last quarter.

Interactive Text Graph Mining with a Prolog-based Dialog Engine

2 code implementations31 Jul 2020 Paul Tarau, Eduardo Blanco

Working on the Prolog facts and their inferred consequences, the dialog engine specializes the text graph with respect to a query and reveals interactively the document's most relevant content elements.

Graph Mining Sentence

Predicting the Focus of Negation: Model and Error Analysis

no code implementations ACL 2020 Md Mosharaf Hossain, Kathleen Hamilton, Alexis Palmer, Eduardo Blanco

The focus of a negation is the set of tokens intended to be negated, and a key component for revealing affirmative alternatives to negated utterances.

Negation

Beyond Possession Existence: Duration and Co-Possession

no code implementations ACL 2020 Dhivya Chinnappa, Srikala Murugan, Eduardo Blanco

This paper introduces two tasks: determining (a) the duration of possession relations and (b) co-possessions, i. e., whether multiple possessors possess a possessee at the same time.

WikiPossessions: Possession Timeline Generation as an Evaluation Benchmark for Machine Reading Comprehension of Long Texts

no code implementations LREC 2020 Dhivya Chinnappa, Alexis Palmer, Eduardo Blanco

Specifically, to complete the full TOP task for a given article, a system must do the following: a) identify possessors; b) anchor possessors to times/events; c) identify temporal relations between each temporal anchor and the possession relation it corresponds to; d) assign certainty scores to each possessor and each temporal relation; and e) assemble individual possession events into a global possession timeline.

Machine Reading Comprehension Relation +1

Extracting Possessions from Social Media: Images Complement Language

no code implementations IJCNLP 2019 Dhivya Chinnappa, Srikala Murugan, Eduardo Blanco

This paper describes a new dataset and experiments to determine whether authors of tweets possess the objects they tweet about.

Word Embeddings

Dependency-based Text Graphs for Keyphrase and Summary Extraction with Applications to Interactive Content Retrieval

2 code implementations20 Sep 2019 Paul Tarau, Eduardo Blanco

We build a bridge between neural network-based machine learning and graph-based natural language processing and introduce a unified approach to keyphrase, summary and relation extraction by aggregating dependency graphs from links provided by a deep-learning based dependency parser.

Relation Relation Extraction +2

Possessors Change Over Time: A Case Study with Artworks

no code implementations EMNLP 2018 Dhivya Chinnappa, Eduardo Blanco

This paper presents a corpus and experimental results to extract possession relations over time.

Dimensions of Interpersonal Relationships: Corpus and Experiments

no code implementations EMNLP 2017 Farzana Rashid, Eduardo Blanco

This paper presents a corpus and experiments to determine dimensions of interpersonal relationships.

Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.