Modeling Composite Labels for Neural Morphological Tagging

Tkachenko, A. I.; Sirts, Kairit

doi:10.18653/v1/k18-1036

Cited by 8 publications

(22 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, there exists no morphological parser that performs both analysis and disambiguation of morphemes in Sanskrit, leaving aside the Cliq-EBM-P configuration reported in Krishna et al (2018). Instead, as baselines, we utilize two widely used neural sequence taggers that reported state-of-the-art results on multiple morphologically rich languages, the FCRF (Malaviya, Gormley, and Neubig 2018) and SeqGen (Tkachenko and Sirts 2018). But they predict only the morphological tag of each word.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Graph-Based Framework for Structured Prediction Tasks in Sanskrit

Krishna

Santra

Gupta

et al. 2021

Computational Linguistics

View full text Add to dashboard Cite

We propose a framework using Energy Based Models for multiple structured prediction tasks in Sanskrit. Ours is an arc-factored model, similar to the graph based parsing approaches, and we consider the tasks of word-segmentation, morphological parsing, dependency parsing, syntactic linearisation and prosodification, a prosody level task we introduce in this work. Ours is a search based structured prediction framework, which expects a graph as input, where relevant linguistic information is encoded in the nodes, and the edges are then used to indicate the association between these nodes. Typically the state of the art models for morphosyntactic tasks in morphologically rich languages still rely on hand-crafted features for their performance. But here, we automate the learning of the feature function. The feature function so learnt along with the search space we construct, encode relevant linguistic information for the tasks we consider. This enables us to substantially reduce the training data requirements to as low as 10 % as compared to the data requirements for the neural state of the art models. Our experiments in Czech and Sanskrit show the language agnostic nature of the framework, where we train highly competitive models for both the languages. Moreover, our framework enables to incorporate language specific constraints to prune the search space and to filter the candidates during inference. We obtain significant improvements in morphosyntactic tasks for Sanskrit by incorporating language specific constraints into the model. In all the tasks we discuss for Sanskrit, we either achieve state of the art results or ours is the only data driven solution for those tasks.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Sequence Generation Model (SeqGen). The model, proposed in Tkachenko and Sirts (2018), also treats the label as a composite label. Here, a char-BiLSTM is used to obtain wordembeddings, which are then passed on to a word-level BiLSTM as the input features (Lample et al 2016;Heigold, Neumann, and van Genabith 2017).…”

Section: Morphological Parsingmentioning

confidence: 99%

A Graph-Based Framework for Structured Prediction Tasks in Sanskrit

Krishna

Santra

Gupta

et al. 2021

Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…More details can be found in Appendix Section §C. Tkachenko and Sirts (2018) also model dependence on POS with a POS-dependent context vector in the decoder. However, they observe no significant improvement; we hypothesize that incorporating POS information into the shared encoder instead provides the model with a stronger signal.…”

Section: Discussionmentioning

confidence: 99%

CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology

Chaudhary¹,

Salesky²,

Bhat³

et al. 2019

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

This paper presents the submission by the CMU-01 team to the SIGMORPHON 2019 task 2 of Morphological Analysis and Lemmatization in Context. This task requires us to produce the lemma and morpho-syntactic description of each token in a sequence, for 107 treebanks. We approach this task with a hierarchical neural conditional random field (CRF) model which predicts each coarse-grained feature (eg. POS, Case, etc.) independently. However, most treebanks are under-resourced, thus making it challenging to train deep neural models for them. Hence, we propose a multi-lingual transfer training regime where we transfer from multiple related languages that share similar typology. 1 Cohen. 2016.Multi-task cross-lingual sequence tagging from scratch. arXiv preprint arXiv:1603.06270.

show abstract

“…To account for the potential dependence between predicted tag dimensions, we feed the encoded representation of each word as the initial hidden states of a GRU (Gated Recurrent Unit, Cho et al, 2014) decoder, which is then trained to predict one tag dimension at each decoding timestep. The use of such a seq2seq model is also partly motivated by its state-of-the-art performance in various NLP tasks such as machine translation (Bahdanau et al, 2015;Luong et al, 2015), document classification (Nam et al, 2017;Yang et al, 2018), morphological reinflection (Kann and Schütze, 2016;Kann et al, 2017), and morphological analysis like the current shared task (Tkachenko and Sirts, 2018). Our seq2seq model resembles Tkachenko and Sirts's (2018) SEQ model, with the primary difference being the use of a GRU decoder (instead of their unidirectional LSTM) and the sorting of tag dimensions in decreasing order of frequency Our seq2seq model strongly outperforms the official baseline, scoring 14.25 and 4.6 points higher on average across 107 datasets on exact match accuracy and micro-averaged F1 scores respectively.…”

Section: Model Descriptionmentioning

confidence: 99%

“…Furthermore, to explicitly incorporate the underlying structure between MSD tag dimensions, the binary relevance model could be extended to a multiclass multilabel classifier, which selects one tag among those that are in complementary distribution for each morphological category (e.g. part-of-speech, case, number) as in Tkachenko and Sirts (2018). Finally, a more rig-orous search for the optimal hyperparameters (e.g.…”

Section: Lengths Of Tag Sequencesmentioning

confidence: 99%

THOMAS: The Hegemonic OSU Morphological Analyzer using Seq2seq

Oh¹,

Maneriker²,

Jiang³

2019

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

This paper describes the OSU submission to the SIGMORPHON 2019 shared task, Crosslinguality and Context in Morphology. Our system addresses the contextual morphological analysis subtask of Task 2, which is to produce the morphosyntactic description (MSD) of each fully inflected word within a given sentence. We frame this as a sequence generation task and employ a neural encoder-decoder (seq2seq) architecture to generate the sequence of MSD tags given the encoded representation of each token. Followup analyses reveal that our system most significantly improves performance on morphologically complex languages whose inflected word forms typically have longer MSD tag sequences. In addition, our system seems to capture the structured correlation between MSD tags, such as that between the verb V tag and TAM-related tags.

show abstract

Modeling Composite Labels for Neural Morphological Tagging

Cited by 8 publications

References 26 publications

A Graph-Based Framework for Structured Prediction Tasks in Sanskrit

A Graph-Based Framework for Structured Prediction Tasks in Sanskrit

CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology

THOMAS: The Hegemonic OSU Morphological Analyzer using Seq2seq

Contact Info

Product

Resources

About