Subword Pooling Makes a Difference (2021.eacl-main)

Copied to clipboard

Challenge: Contextual word-representations use subword tokenization to handle large vocabularies and unknown words.
Approach: They propose to use the first subword for morphological probing, POS tagging and NER to pool multiple subwords that correspond to a single word in contextual language models.
Outcome: The proposed model outperforms two multilingual models on morphological probing, POS tagging and NER tasks in 9 languages.

Similar Papers

Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing across Languages and Domains (2024.lrec-main)

Copied to clipboard

Challenge: Neural parsing is dependent on the underlying language model, but little is known about how choices affect parser performance.
Approach: They examine how subword sharing is responsible for gains or negative transfer in multi-task learning . they find a preference for averaged or last subwords across languages and domains .
Outcome: The proposed model favors averaged or last subwords across languages and domains . specific POS tags may require different subword, and distribution overlap is more important than discrepancies in the data sizes.
Learn Your Tokens: Word-Pooled Tokenization for Language Modeling (2023.findings-emnlp)

Copied to clipboard

Challenge: Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as ‘ing’ or whole words.
Approach: They propose a 'learn your tokens' scheme which pooles bytes/characters into word representations and decodes individual characters/bytes per word in parallel.
Outcome: The proposed tokenizer outperforms subword models and byte/character models over the word boundary and outperformed on rare words by a factor of 30!
Unlike “Likely”, “Unlike” is Unlikely: BPE-based Segmentation hurts Morphological Derivations in LLMs (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) use subword vocabularies to process and generate text.
Approach: They find that Large Language Models (LLMs) perform poorly at handling some types of affixations because subwords are marked as initial- or intra-word .
Outcome: The largest models trained on enough data can mitigate this tendency because initial- and intra-word embeddings are aligned; in-context learning also helps when all examples are selected in a consistent way; but only morphological segmentation can achieve a near-perfect accuracy.
A Systematic Study of Leveraging Subword Information for Learning Word Representations (N19-1)

Copied to clipboard

Challenge: Existing word representation models for morphologically rich languages use subword-level information, but their systematic comparative analysis across typologically diverse languages and tasks is still missing.
Approach: They propose a framework for learning subword-informed word representations that allows for easy experimentation with different segmentation and composition components.
Outcome: The proposed framework allows for easy experimentation with different segmentation and composition components, as well as advanced techniques based on position embeddings and self-attention.
Tokenization Falling Short: On Subword Robustness in Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary.
Approach: They propose to tokenize raw text into sequences of subword identifiers from a predefined vocabulary . they also investigate the challenges and their impact on large language models .
Outcome: The proposed model can mitigate tokenization issues, but still suffer from typos and other variations.
The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation (2021.eacl-srw)

Copied to clipboard

Challenge: Current NMT systems typically operate at the level of subwords, causing problems of vocabulary sparsity.
Approach: They compare subword segmentation methods with morphologically-based methods in a low-resource setting . they find that no consistent and reliable differences emerge between the methods .
Outcome: The proposed methods outperform BPE in a low-resource translation setting.
Revisiting subword tokenization: A case study on affixal negation in large language models (2024.naacl-long)

Copied to clipboard

Challenge: Negation is central to language understanding but is not properly captured by modern NLP methods.
Approach: They propose to use subword tokenization methods to detect negation in large language models . they find that models can reliably recognize negation, despite mismatches in tokenization accuracy .
Outcome: The proposed models can detect negation in English using subword tokenization methods despite some mismatches in tokenization accuracy and negation detection performance.
Why and when should you pool? Analyzing Pooling in Recurrent Architectures (2020.findings-emnlp)

Copied to clipboard

Challenge: Various pooling techniques have been shown to improve performance of RNNs on text classification tasks.
Approach: They propose a pooling-based variant that captures interactions among predictive tokens in a sentence.
Outcome: The proposed pooling architecture outperforms non-pooling models on sequence classification tasks.
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms (P18-1)

Copied to clipboard

Challenge: Existing deep learning architectures to model compositionality in text sequences require a large number of parameters and expensive computations.
Approach: They propose two additional pooling strategies over word embeddings for improved interpretability and hierarchical pooling for spatial (n-gram) information within text sequences.
Outcome: The proposed pooling strategies improve interpretability and preserve spatial (n-gram) information within text sequences.
How Important Is Tokenization in French Medical Masked Language Models? (2024.lrec-main)

Copied to clipboard

Challenge: Word tokenization into subword units has become the prevailing standard in the field of natural language processing (NLP) over recent years . the precise factors contributing to its success remain unclear .
Approach: They propose a tokenization strategy that integrates morpheme-enriched word segmentation into existing tokenization methods.
Outcome: The proposed tokenization strategy outperforms character and word tokenization but the precise factors contributing to its success remain unclear.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations