Viable Dependency Parsing as Sequence Labeling

Abstract

We recast dependency parsing as a sequence labeling problem, exploring several encodings of dependency trees as labels. While dependency parsing by means of sequence labeling had been attempted in existing work, results suggested that the technique was impractical. We show instead that with a conventional BIL-STM-based model it is possible to obtain fast and accurate parsers. These parsers are conceptually simple, not needing traditional parsing algorithms or auxiliary structures. However, experiments on the PTB and a sample of UD treebanks show that they provide a good speed-accuracy tradeoff, with results competitive with more complex approaches.

Towards Making a Dependency Parser See

“…This also opens the question of whether a different architecture could better suit the purpose of leveraging the gaze information in a consistent way. In this context, a potential line of work could adapt human-attention approaches (Barrett et al, 2018) for structured prediction and word-level classification, although it would come at a cost of speed for parsing as sequence labeling (Strzyz et al, 2019b).…”

“…Dependency parsing as sequence labeling We proceed similarly to Strzyz et al (2019b). Given a linearization function F w :…”

“…To do so, we rely on MTL and auxiliary tasks. Our work focuses on exploiting the utility of gaze information using just a standard BILSTM, directly building on top of previous work of dependency parsing as sequence labeling (Strzyz et al, 2019b), and ignoring extra tools such as attention. In this line, a future possible solution could be to apply the approach by Barrett et al (2018) to structured prediction and word-level classification.…”

Artificially Evolved Chunks for Morphosyntactic Analysis

“…Experiment 2 We used the best predictions (when using chunking) from experiment 1 as additional features for a sequence-labelling dependency parser (Strzyz et al, 2019). Therefore, network input consisted of word and character embedding and then some combination of POS tags, morphological feature tags, or chunk labels with the sole output being a dependency parser tag.…”

Sequence Labeling Parsing by Learning across Representations

“…Figure 1a illustrates the encoding with an example. 1 Dependency parsing as tagging Strzyz et al (2019) also propose a linearization method Π |w| :…”