Search Results for author: Gerard de Melo

Found 75 papers, 22 papers with code

EmoTag1200: Understanding the Association between Emojis and Emotions

no code implementations EMNLP 2020 Abu Awal Md Shoeb, Gerard de Melo

Given the growing ubiquity of emojis in language, there is a need for methods and resources that shed light on their meaning and communicative role.

Data Augmentation with Adversarial Training for Cross-Lingual NLI

no code implementations ACL 2021 Xin Dong, Yaxin Zhu, Zuohui Fu, Dongkuan Xu, Gerard de Melo

Due to recent pretrained multilingual representation models, it has become feasible to exploit labeled data from one language to train a cross-lingual model that can then be applied to multiple new languages.

Cross-Lingual Natural Language Inference Data Augmentation

R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling

1 code implementation ACL 2021 Xiang Hu, Haitao Mi, Zujie Wen, Yafang Wang, Yi Su, Jing Zheng, Gerard de Melo

Human language understanding operates at multiple levels of granularity (e. g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined.

Language Modelling

Guilt by Association: Emotion Intensities in Lexical Representations

no code implementations18 Apr 2021 Shahab Raji, Gerard de Melo

What do word vector representations reveal about the emotions associated with words?

Context-Aware Interaction Network for Question Matching

no code implementations17 Apr 2021 Zhe Hu, Zuohui Fu, Yu Yin, Gerard de Melo

Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations.

Text Matching

Faithfully Explainable Recommendation via Neural Logic Reasoning

1 code implementation NAACL 2021 Yaxin Zhu, Yikun Xian, Zuohui Fu, Gerard de Melo, Yongfeng Zhang

Knowledge graphs (KG) have become increasingly important to endow modern recommender systems with the ability to generate traceable reasoning paths to explain the recommendation process.

Decision Making Knowledge Graphs +1

Fast and Effective Biomedical Entity Linking Using a Dual Encoder

1 code implementation8 Mar 2021 Rajarshi Bhowmik, Karl Stratos, Gerard de Melo

Additionally, we modify our dual encoder model for end-to-end biomedical entity linking that performs both mention span detection and entity disambiguation and out-performs two recently proposed models.

Entity Disambiguation Entity Linking

Assessing Emoji Use in Modern Text Processing Tools

no code implementations ACL 2021 Abu Awal Md Shoeb, Gerard de Melo

Emojis have become ubiquitous in digital communication, due to their visual appeal as well as their ability to vividly convey human emotion, among other factors.

Part-Of-Speech Tagging Sentiment Analysis +1

Interactive Question Clarification in Dialogue via Reinforcement Learning

no code implementations COLING 2020 Xiang Hu, Zujie Wen, Yafang Wang, Xiaolong Li, Gerard de Melo

In this work, we propose a reinforcement model to clarify ambiguous questions by suggesting refinements of the original query.

Query Distillation: BERT-based Distillation for Ensemble Ranking

no code implementations COLING 2020 Wangshu Zhang, Junhong Liu, Zujie Wen, Yafang Wang, Gerard de Melo

We present a novel two-stage distillation method for ranking problems that allows a smaller student model to be trained while benefitting from the better performance of the teacher model, providing better control of the inference latency and computational burden.

Knowledge Distillation

Domain-Specific Sentiment Lexicons Induced from Labeled Documents

no code implementations COLING 2020 Sm Mazharul Islam, Xin Dong, Gerard de Melo

Sentiment analysis is an area of substantial relevance both in industry and in academia, including for instance in social studies.

Sentiment Analysis

Sentence Analogies: Linguistic Regularities in Sentence Embeddings

no code implementations COLING 2020 Xunjie Zhu, Gerard de Melo

While important properties of word vector representations have been studied extensively, far less is known about the properties of sentence vector representations.

Sentence Embedding

Cross-Domain Learning for Classifying Propaganda in Online Contents

2 code implementations13 Nov 2020 Liqiang Wang, Xiaoyu Shen, Gerard de Melo, Gerhard Weikum

Prior work has focused on supervised learning with training data from the same domain.

CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation

1 code implementation29 Oct 2020 Yikun Xian, Zuohui Fu, Handong Zhao, Yingqiang Ge, Xu Chen, Qiaoying Huang, Shijie Geng, Zhou Qin, Gerard de Melo, S. Muthukrishnan, Yongfeng Zhang

User profiles can capture prominent user behaviors from the history, and provide valuable signals about which kinds of path patterns are more likely to lead to potential items of interest for the user.

Knowledge Graphs Recommendation Systems

GitEvolve: Predicting the Evolution of GitHub Repositories

1 code implementation9 Oct 2020 Honglu Zhou, Hareesh Ravi, Carlos M. Muniz, Vahid Azizi, Linda Ness, Gerard de Melo, Mubbasir Kapadia

Given its crucial role, there is a need to better understand and model the dynamics of GitHub as a social platform.

Representation Learning

COOKIE: A Dataset for Conversational Recommendation over Knowledge Graphs in E-commerce

no code implementations21 Aug 2020 Zuohui Fu, Yikun Xian, Yaxin Zhu, Yongfeng Zhang, Gerard de Melo

In this work, we present a new dataset for conversational recommendation over knowledge graphs in e-commerce platforms called COOKIE.

Knowledge Graphs

Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification

no code implementations29 Jul 2020 Xin Dong, Yaxin Zhu, Yupeng Zhang, Zuohui Fu, Dongkuan Xu, Sen yang, Gerard de Melo

The resulting model then serves as a teacher to induce labels for unlabeled target language samples that can be used during further adversarial training, allowing us to gradually adapt our model to the target language.

Classification General Classification +2

Contrastive Visual-Linguistic Pretraining

no code implementations26 Jul 2020 Lei Shi, Kai Shuang, Shijie Geng, Peng Su, Zhengkai Jiang, Peng Gao, Zuohui Fu, Gerard de Melo, Sen Su

We evaluate CVLP on several down-stream tasks, including VQA, GQA and NLVR2 to validate the superiority of contrastive learning on multi-modality representation learning.

Contrastive Learning Representation Learning +1

Incorporating Pragmatic Reasoning Communication into Emergent Language

no code implementations NeurIPS 2020 Yipeng Kang, Tonghan Wang, Gerard de Melo

Emergentism and pragmatics are two research fields that study the dynamics of linguistic communication along substantially different timescales and intelligence levels.

Multi-agent Reinforcement Learning Starcraft +1

Fairness-Aware Explainable Recommendation over Knowledge Graphs

1 code implementation3 Jun 2020 Zuohui Fu, Yikun Xian, Ruoyuan Gao, Jieyu Zhao, Qiaoying Huang, Yingqiang Ge, Shuyuan Xu, Shijie Geng, Chirag Shah, Yongfeng Zhang, Gerard de Melo

There has been growing attention on fairness considerations recently, especially in the context of intelligent decision making systems.

Decision Making Fairness +3

TIME: Text and Image Mutual-Translation Adversarial Networks

no code implementations27 May 2020 Bingchen Liu, Kunpeng Song, Yizhe Zhu, Gerard de Melo, Ahmed Elgammal

Focusing on text-to-image (T2I) generation, we propose Text and Image Mutual-Translation Adversarial Networks (TIME), a lightweight but effective model that jointly learns a T2I generator G and an image captioning discriminator D under the Generative Adversarial Network framework.

Image Captioning Language Modelling +1

Character Matters: Video Story Understanding with Character-Aware Relations

no code implementations9 May 2020 Shijie Geng, Ji Zhang, Zuohui Fu, Peng Gao, Hang Zhang, Gerard de Melo

Without identifying the connection between appearing people and character names, a model is not able to obtain a genuine understanding of the plots.

Question Answering

Are Emojis Emotional? A Study to Understand the Association between Emojis and Emotions

no code implementations2 May 2020 Abu Shoeb, Gerard de Melo

Given the growing ubiquity of emojis in language, there is a need for methods and resources that shed light on their meaning and communicative role.

Explainable Link Prediction for Emerging Entities in Knowledge Graphs

1 code implementation1 May 2020 Rajarshi Bhowmik, Gerard de Melo

Despite their large-scale coverage, cross-domain knowledge graphs invariably suffer from inherent incompleteness and sparsity.

Knowledge Graphs Link Prediction +1

Inducing Universal Semantic Tag Vectors

no code implementations LREC 2020 Da Huo, Gerard de Melo

Given the well-established usefulness of part-of-speech tag annotations in many syntactically oriented downstream NLP tasks, the recently proposed notion of semantic tagging (Bjerva et al. 2016) aims at tagging words with tags informed by semantic distinctions, which are likely to be useful across a range of semantic tasks.

HID: Hierarchical Multiscale Representation Learning for Information Diffusion

2 code implementations19 Apr 2020 Honglu Zhou, Shuyuan Xu, Zuohui Fu, Gerard de Melo, Yongfeng Zhang, Mubbasir Kapadia

In this paper, we present a Hierarchical Information Diffusion (HID) framework by integrating user representation learning and multiscale modeling.

Representation Learning

Sentence Analogies: Exploring Linguistic Relationships and Regularities in Sentence Embeddings

no code implementations9 Mar 2020 Xunjie Zhu, Gerard de Melo

While important properties of word vector representations have been studied extensively, far less is known about the properties of sentence vector representations.

Sentence Embedding

Knowledge Graphs

2 code implementations4 Mar 2020 Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d'Amato, Gerard de Melo, Claudio Gutierrez, José Emilio Labra Gayo, Sabrina Kirrane, Sebastian Neumaier, Axel Polleres, Roberto Navigli, Axel-Cyrille Ngonga Ngomo, Sabbir M. Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab, Antoine Zimmermann

In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data.

Knowledge Graphs

Long Short-Term Sample Distillation

no code implementations2 Mar 2020 Liang Jiang, Zujie Wen, Zhongping Liang, Yafang Wang, Gerard de Melo, Zhe Li, Liangzhuang Ma, Jiaxing Zhang, Xiaolong Li, Yuan Qi

The long-term teacher draws on snapshots from several epochs ago in order to provide steadfast guidance and to guarantee teacher--student differences, while the short-term one yields more up-to-date cues with the goal of enabling higher-quality updates.

ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs

1 code implementation29 Jan 2020 Zuohui Fu, Yikun Xian, Shijie Geng, Yingqiang Ge, Yuting Wang, Xin Dong, Guang Wang, Gerard de Melo

A number of cross-lingual transfer learning approaches based on neural networks have been proposed for the case when large amounts of parallel text are at our disposal.

Cross-Lingual Transfer Sentence Embedding +1

Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation

no code implementations18 Dec 2019 Xin Dong, Jingchao Ni, Wei Cheng, Zhengzhang Chen, Bo Zong, Dongjin Song, Yanchi Liu, Haifeng Chen, Gerard de Melo

In practice, however, these two sets of reviews are notably different: users' reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item's reviews pertain only to that single item and are thus topically homogeneous.

Recommendation Systems

A Robust Self-Learning Framework for Cross-Lingual Text Classification

no code implementations IJCNLP 2019 Xin Dong, Gerard de Melo

Based on massive amounts of data, recent pretrained contextual representation models have made significant strides in advancing a number of different English NLP tasks.

Classification General Classification +2

SCALOR: Generative World Models with Scalable Object Representations

2 code implementations ICLR 2020 Jindong Jiang, Sepehr Janghorbani, Gerard de Melo, Sungjin Ahn

Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning.

Representation Learning

EmoTag -- Towards an Emotion-Based Analysis of Emojis

no code implementations RANLP 2019 Abu Awal Md Shoeb, Shahab Raji, Gerard de Melo

We evaluate the induced emotion profiles of emojis with regard to their ability to predict word affect intensities as well as sentiment scores.

Reinforcement Knowledge Graph Reasoning for Explainable Recommendation

1 code implementation12 Jun 2019 Yikun Xian, Zuohui Fu, S. Muthukrishnan, Gerard de Melo, Yongfeng Zhang

To this end, we propose a method called Policy-Guided Path Reasoning (PGPR), which couples recommendation and interpretability by providing actual paths in a knowledge graph.

Causal Inference Decision Making +1

OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization

1 code implementation26 May 2019 Bingchen Liu, Yizhe Zhu, Zuohui Fu, Gerard de Melo, Ahmed Elgammal

Exploring the potential of GANs for unsupervised disentanglement learning, this paper proposes a novel GAN-based disentanglement framework with One-Hot Sampling and Orthogonal Regularization (OOGAN).

Be Concise and Precise: Synthesizing Open-Domain Entity Descriptions from Facts

1 code implementation16 Apr 2019 Rajarshi Bhowmik, Gerard de Melo

Despite being vast repositories of factual information, cross-domain knowledge graphs, such as Wikidata and the Google Knowledge Graph, only sparsely provide short synoptic descriptions for entities.

Entity Disambiguation Knowledge Graphs

CITE: A Corpus of Image-Text Discourse Relations

1 code implementation NAACL 2019 Malihe Alikhani, Sreyasi Nag Chowdhury, Gerard de Melo, Matthew Stone

This paper presents a novel crowd-sourced resource for multimodal discourse: our resource characterizes inferences in image-text contexts in the domain of cooking recipes in the form of coherence relations.

Common Sense Reasoning

Using Multi-Sense Vector Embeddings for Reverse Dictionaries

1 code implementation WS 2019 Michael A. Hedderich, Andrew Yates, Dietrich Klakow, Gerard de Melo

However, they typically cannot serve as a drop-in replacement for conventional single-sense embeddings, because the correct sense vector needs to be selected for each word.

A Helping Hand: Transfer Learning for Deep Sentiment Analysis

no code implementations ACL 2018 Xin Dong, Gerard de Melo

Deep convolutional neural networks excel at sentiment polarity classification, but tend to require substantial amounts of training data, which moreover differs quite significantly between domains.

General Classification Sentiment Analysis +2

Generating Fine-Grained Open Vocabulary Entity Type Descriptions

1 code implementation ACL 2018 Rajarshi Bhowmik, Gerard de Melo

While large-scale knowledge graphs provide vast amounts of structured facts about entities, a short textual description can often be useful to succinctly characterize an entity and its type.

Knowledge Graphs

Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification

2 code implementations CVPR 2018 Xiang Long, Chuang Gan, Gerard de Melo, Jiajun Wu, Xiao Liu, Shilei Wen

In this paper, however, we show that temporal information, especially longer-term patterns, may not be necessary to achieve competitive results on common video classification datasets.

Classification General Classification +1

Multilingual Vector Representations of Words, Sentences, and Documents

no code implementations IJCNLP 2017 Gerard de Melo

Neural vector representations are now ubiquitous in all subfields of natural language processing and text mining.

Knowledge Graphs

Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval

3 code implementations30 Jun 2017 Kai Hui, Andrew Yates, Klaus Berberich, Gerard de Melo

Neural IR models, such as DRMM and PACRR, have achieved strong results by successfully capturing relevance matching signals.

Ad-Hoc Information Retrieval

PACRR: A Position-Aware Neural IR Model for Relevance Matching

3 code implementations EMNLP 2017 Kai Hui, Andrew Yates, Klaus Berberich, Gerard de Melo

In order to adopt deep learning for information retrieval, models are needed that can capture all relevant information required to assess the relevance of a document to a given user query.

Ad-Hoc Information Retrieval Information Retrieval

Video Captioning with Multi-Faceted Attention

no code implementations TACL 2018 Xiang Long, Chuang Gan, Gerard de Melo

Recently, video captioning has been attracting an increasing amount of interest, due to its potential for improving accessibility and information retrieval.

Information Retrieval Video Captioning

Should Algorithms for Random SAT and Max-SAT be Different?

no code implementations3 Oct 2016 Sixue Liu, Gerard de Melo

We analyze to what extent the random SAT and Max-SAT problems differ in their properties.

Medical Concept Embeddings via Labeled Background Corpora

no code implementations LREC 2016 Eneldo Loza Menc{\'\i}a, Gerard de Melo, Jinseok Nam

In recent years, we have seen an increasing amount of interest in low-dimensional vector representations of words.

Word Similarity

The Open Linguistics Working Group: Developing the Linguistic Linked Open Data Cloud

no code implementations LREC 2016 John Philip McCrae, Christian Chiarcos, Francis Bond, Philipp Cimiano, Thierry Declerck, Gerard de Melo, Jorge Gracia, Sebastian Hellmann, Bettina Klimek, Steven Moran, Petya Osenova, Antonio Pareja-Lora, Jonathan Pool

The Open Linguistics Working Group (OWLG) brings together researchers from various fields of linguistics, natural language processing, and information technology to present and discuss principles, case studies, and best practices for representing, publishing and linking linguistic data collections.

NomLex-PT: A Lexicon of Portuguese Nominalizations

no code implementations LREC 2014 Valeria de Paiva, Livy Real, Alex Rademaker, re, Gerard de Melo

This paper presents NomLex-PT, a lexical resource describing Portuguese nominalizations.

Bring vs. MTRoget: Evaluating automatic thesaurus translation

no code implementations LREC 2014 Lars Borin, Jens Allwood, Gerard de Melo

Evaluation of automatic language-independent methods for language technology resource creation is difficult, and confounded by a largely unknown quantity, viz.

Etymological Wordnet: Tracing The History of Words

no code implementations LREC 2014 Gerard de Melo

Research on the history of words has led to remarkable insights about language and also about the history of human civilization more generally.

Empirical Comparisons of MASC Word Sense Annotations

no code implementations LREC 2012 Gerard de Melo, Collin F. Baker, Nancy Ide, Rebecca J. Passonneau, Christiane Fellbaum

We analyze how different conceptions of lexical semantics affect sense annotations and how multiple sense inventories can be compared empirically, based on annotated text.

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