From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language Understanding

Li Sun, Florian Luisier, Kayhan Batmanghelich, Dinei Florencio, Cha Zhang

Main: Large Language Models Main-poster Paper

Session 7: Large Language Models (Virtual Poster)
Conference Room: Pier 7&8
Conference Time: July 12, 11:00-12:30 (EDT) (America/Toronto)
Global Time: July 12, Session 7 (15:00-16:30 UTC)
Keywords: pre-training
TLDR: Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens. This process known as tokenization relies on a pre-built vocabulary of words or sub-word morphemes. This fixed vocabulary limits the model's robustness to spellin...
You can open the #paper-P518 channel in a separate window.
Abstract: Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens. This process known as tokenization relies on a pre-built vocabulary of words or sub-word morphemes. This fixed vocabulary limits the model's robustness to spelling errors and its capacity to adapt to new domains. In this work, we introduce a novel open-vocabulary language model that adopts a hierarchical two-level approach: one at the word level and another at the sequence level. Concretely, we design an intra-word module that uses a shallow Transformer architecture to learn word representations from their characters, and a deep inter-word Transformer module that contextualizes each word representation by attending to the entire word sequence. Our model thus directly operates on character sequences with explicit awareness of word boundaries, but without biased sub-word or word-level vocabulary. Experiments on various downstream tasks show that our method outperforms strong baselines. We also demonstrate that our hierarchical model is robust to textual corruption and domain shift.