Papers › Learning Better Internal Structure of Words for Sequence Labeling

Learning Better Internal Structure of Words for Sequence Labeling

29 Oct 2018EMNLP 2018 10arXiv:1810.12443archive 2025-07-28

Yingwei Xin, Ethan Hart, Vibhuti Mahajan, Jean-David Ruvini

Character-based neural models have recently proven very useful for many NLP tasks. However, there is a gap of sophistication between methods for learning representations of sentences and words. While most character models for learning representations of sentences are deep and complex, models for learning representations of words are shallow and simple. Also, in spite of considerable research on learning character embeddings, it is still not clear which kind of architecture is the best for capturing character-to-word representations. To address these questions, we first investigate the gaps between methods for learning word and sentence representations. We conduct detailed experiments and comparisons of different state-of-the-art convolutional models, and also investigate the advantages and disadvantages of their constituents. Furthermore, we propose IntNet, a funnel-shaped wide convolutional neural architecture with no down-sampling for learning representations of the internal structure of words by composing their characters from limited, supervised training corpora. We evaluate our proposed model on six sequence labeling datasets, including named entity recognition, part-of-speech tagging, and syntactic chunking. Our in-depth analysis shows that IntNet significantly outperforms other character embedding models and obtains new state-of-the-art performance without relying on any external knowledge or resources.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ChunkingNamed Entity RecognitionNamed Entity Recognition (NER)Part-Of-Speech TaggingSentencenamed-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Chunking Penn Treebank IntNet + BiLSTM-CRF F1 score 95.29 #5 of 8 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) IntNet + BiLSTM-CRF F1 91.64 #56 of 73 Archive leaderboard report
Part-Of-Speech Tagging Penn Treebank IntNet + BiLSTM-CRF Accuracy 97.58 #9 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections