Search Results for author:
Found 40 papers, 16 papers with code
All-but-the-Top: Simple and Effective Postprocessing for Word Representations
The postprocessing is empirically validated on a variety of lexical-level intrinsic tasks (word similarity, concept categorization, word analogy) and sentence-level tasks (semantic textural similarity and { text classification}) on multiple datasets and with a variety of representation methods and hyperparameter choices in multiple languages; in each case, the processed representations are consistently better than the original ones.
Ranked #11 on
Sentiment Analysis
on MR
Document Similarity for Texts of Varying Lengths via Hidden Topics
This is because of the lexical, contextual and the abstraction gaps between a long document of rich details and its concise summary of abstract information.
Self-Supervised Euphemism Detection and Identification for Content Moderation
It is usually apparent to a human moderator that a word is being used euphemistically, but they may not know what the secret meaning is, and therefore whether the message violates policy.
Euphemistic Phrase Detection by Masked Language Model
It is a well-known approach for fringe groups and organizations to use euphemisms -- ordinary-sounding and innocent-looking words with a secret meaning -- to conceal what they are discussing.
GRUEN for Evaluating Linguistic Quality of Generated Text
Automatic evaluation metrics are indispensable for evaluating generated text.
Idiomatic Expression Identification using Semantic Compatibility
Idiomatic expressions are an integral part of natural language and constantly being added to a language.
Geometry of Compositionality
This paper proposes a simple test for compositionality (i. e., literal usage) of a word or phrase in a context-specific way.
FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams
In this paper, we study the task of multi-faceted set expansion, which aims to capture all semantic facets in the seed set and return multiple sets of entities, one for each semantic facet.
Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention
Abusive language is a massive problem in online social platforms.
Enriching Word Embeddings with Temporal and Spatial Information
The meaning of a word is closely linked to sociocultural factors that can change over time and location, resulting in corresponding meaning changes.
CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family
We design a principled curriculum, guided by information-theoretic insights, to train CRISP and show that it outperforms the successive-cancellation (SC) decoder and attains near-optimal reliability performance on the Polar(32, 16) and Polar(64, 22) codes.
Preposition Sense Disambiguation and Representation
Prepositions are highly polysemous, and their variegated senses encode significant semantic information.
IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions
Unlike prior works that enable IE comprehension through fine-tuning PTLMs with sentences containing IEs, in this work, we construct IEKG, a commonsense knowledge graph for figurative interpretations of IEs.
Embedding Syntax and Semantics of Prepositions via Tensor Decomposition
Prepositions are among the most frequent words in English and play complex roles in the syntax and semantics of sentences.
MORSE: Semantic-ally Drive-n MORpheme SEgment-er
We present in this paper a novel framework for morpheme segmentation which uses the morpho-syntactic regularities preserved by word representations, in addition to orthographic features, to segment words into morphemes.
Representing Sentences as Low-Rank Subspaces
Sentences are important semantic units of natural language.
Fixing the Infix: Unsupervised Discovery of Root-and-Pattern Morphology
We present an unsupervised and language-agnostic method for learning root-and-pattern morphology in Semitic languages.
Prepositions in Context
Prepositions are highly polysemous, and their variegated senses encode significant semantic information.
Geometry of Polysemy
Vector representations of words have heralded a transformational approach to classical problems in NLP; the most popular example is word2vec.
Context-Sensitive Malicious Spelling Error Correction
Misspelled words of the malicious kind work by changing specific keywords and are intended to thwart existing automated applications for cyber-environment control such as harassing content detection on the Internet and email spam detection.
Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
Our generator employs an attention-based encoder-decoder to transfer a sentence from the source style to the target style.
Equipping Educational Applications with Domain Knowledge
One of the challenges of building natural language processing (NLP) applications for education is finding a large domain-specific corpus for the subject of interest (e. g., history or science).
PaRe: A Paper-Reviewer Matching Approach Using a Common Topic Space
Finding the right reviewers to assess the quality of conference submissions is a time consuming process for conference organizers.
IlliniMet: Illinois System for Metaphor Detection with Contextual and Linguistic Information
Metaphors are rhetorical use of words based on the conceptual mapping as opposed to their literal use.
From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation
We study a new application for text generation -- idiomatic sentence generation -- which aims to transfer literal phrases in sentences into their idiomatic counterparts.
PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing
Idiomatic expressions (IE) play an important role in natural language, and have long been a “pain in the neck” for NLP systems.
Paraphrase Generation: A Survey of the State of the Art
This paper focuses on paraphrase generation, which is a widely studied natural language generation task in NLP.
Rich Syntactic and Semantic Information Helps Unsupervised Text Style Transfer
Text style transfer aims to change an input sentence to an output sentence by changing its text style while preserving the content.
Context-Aware Automatic Text Simplification of Health Materials in Low-Resource Domains
We also show the enhanced accuracy of our system over directly-supervised neural methods in this low-resource setting.
Idiomatic Expression Paraphrasing without Strong Supervision
In this paper, we study the task of idiomatic sentence paraphrasing (ISP), which aims to paraphrase a sentence with an IE by replacing the IE with its literal paraphrase.
Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions
Idiomatic expressions (IEs), characterized by their non-compositionality, are an important part of natural language.
Unified Representation for Non-compositional and Compositional Expressions
Accurate processing of non-compositional language relies on generating good representations for such expressions.
