paper-with-me

홈 › Papers

Non-distributional Word Vector Representations

2015-06-17 · IJCNLP 2015 7 · Manaal Faruqui, Chris Dyer

Data-driven representation learning for words is a technique of central importance in NLP. While indisputably useful as a source of features in downstream tasks, such vectors tend to consist of uninterpretable components whose relationship to the categories of traditional lexical semantic theories is tenuous at best. We present a method for constructing interpretable word vectors from hand-crafted linguistic resources like WordNet, FrameNet etc. These vectors are binary (i.e, contain only 0 and 1) and are 99.9% sparse. We analyze their performance on state-of-the-art evaluation methods for distributional models of word vectors and find they are competitive to standard distributional approaches.

📄 PDF Abstract BibTeX arXiv:1506.05230

Code (1)

mfaruqui/non-distributional 공식 구현

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Can Network Embedding of Distributional Thesaurus be Combined with Word Vectors for Better Representation?

2018-02-17 · NAACL 2018 6 · Abhik Jana, Pawan Goyal

Distributed representations of words learned from text have proved to be successful in various natural language processing tasks in recent times. While some methods represent words as vectors computed from text using pre…

Network EmbeddingWord Similarity

Sentence Entailment in Compositional Distributional Semantics

2015-12-14 · Esma Balkir, Dimitri Kartsaklis, Mehrnoosh Sadrzadeh

Distributional semantic models provide vector representations for words by gathering co-occurrence frequencies from corpora of text. Compositional distributional models extend these from words to phrases and sentences. I…

Sentence

Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources

2018-05-08 · NAACL 2018 6 · Ivan Vulić, Goran Glavaš, Nikola Mrkšić, Anna Korhonen

Word vector specialisation (also known as retrofitting) is a portable, light-weight approach to fine-tuning arbitrary distributional word vector spaces by injecting external knowledge from rich lexical resources such as …

Dialogue State TrackingText SimplificationWord Similarity

Semantic Word Clusters Using Signed Normalized Graph Cuts

2016-01-20 · João Sedoc, Jean Gallier, Lyle Ungar, Dean Foster

Vector space representations of words capture many aspects of word similarity, but such methods tend to make vector spaces in which antonyms (as well as synonyms) are close to each other. We present a new signed spectral…

ClusteringWord Similarity

Building Sense Representations in Danish by Combining Word Embeddings with Lexical Resources

2020-05-01 · LREC 2020 5 · Ida R{\o}rmann Olsen, Bolette Pedersen, Asad Sayeed

Our aim is to identify suitable sense representations for NLP in Danish. We investigate sense inventories that correlate with human interpretations of word meaning and ambiguity as typically described in dictionaries and…

SentenceWord EmbeddingsWord Sense Disambiguation