• Publications
  • Influence
Weighted Neural Bag-of-n-grams Model: New Baselines for Text Classification
TLDR
We train n-gram embeddings and use NB weighting to guide the neural models to focus on important words. Expand
  • 16
  • 3
  • PDF
Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings
TLDR
We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Expand
  • 28
  • 2
  • PDF
Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics
TLDR
In this paper, we introduce ngrams into four representation methods: SGNS, GloVe, PPMI matrix, and its SVD factorization. Expand
  • 27
  • 2
  • PDF
The (too Many) Problems of Analogical Reasoning with Word Vectors
TLDR
We argue against such “linguistic regularities” as a model for linguistic relations in vector space models and as a benchmark, and we show that the vector offset (as well as two other, better-performing methods) suffers from dependence on vector similarity. Expand
  • 42
  • 1
  • PDF
AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
TLDR
We propose a novel Adaptive BERT compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks. Expand
  • 20
  • 1
  • PDF
Subword-level Composition Functions for Learning Word Embeddings
TLDR
We propose CNN- and RNN-based composition functions for learning word embeddings, and systematically compare them with popular word-level and subword-level models (Skip-Gram and FastText). Expand
  • 15
  • 1
  • PDF
Neural Bag-of-Ngrams
TLDR
We introduce the concept of Neural Bag-of-ngrams (Neural-BoN), which replaces sparse one-hot n-gram representation in traditional BoN with dense and rich-semantic n-ram representations. Expand
  • 12
  • 1
  • PDF
Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews
TLDR
We modify the architecture of the recently proposed Paragraph Vector, allowing it to learn document vectors by predicting not only words, but n-gram features as well. Expand
  • 13
  • 1
  • PDF
YOJ: An online judge system designed for programming courses
TLDR
This paper describes our online judge system (YOJ) which is used to support the teaching of the programming courses, making students to practice programming independently and helping teachers to assign homework on key programming concepts. Expand
  • 4
  • 1
Scaling Word2Vec on Big Corpus
TLDR
Word embedding has been well accepted as an important feature in the area of natural language processing (NLP). Expand
  • 11
...
1
2
3
...