| Challenge: | linguistic interpretations of cognate prediction have been based on external analysis (accuracy, raw results, errors). |
| Approach: | They propose to use character-based machine translation models to store linguistic and diachronic information but not in previously assumed ways. |
| Outcome: | The proposed model stores linguistic and diachronic information but does not achieve it in previously assumed ways. |
Similar Papers
Predicting Reference: What do Language Models Learn about Discourse Models? (2020.emnlp-main)
Copied to clipboard
| Challenge: | a growing literature that probes neural language models to assess their latent acquisition of grammatical knowledge has not investigated their acquisition of discourse modeling ability. |
| Approach: | They draw on a psycholinguistic literature that has established how different contexts affect referential biases concerning who is likely to be referred to next. |
| Outcome: | The proposed models do not resemble human language users, the authors show . their models capture the linguistic knowledge required to perform discourse modeling . |
Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages (2020.coling-main)
Copied to clipboard
Diptesh Kanojia, Raj Dabre, Shubham Dewangan, Pushpak Bhattacharyya, Gholamreza Haffari, Malhar Kulkarni
| Challenge: | a study of 14 Indian languages shows that cognates can be detected by word embeddings . cognates are variants of the same lexical form across languages . |
| Approach: | They propose to use cross-lingual word embeddings to detect cognates among 14 Indian languages . they then evaluate the impact of their method on neural machine translation . |
| Outcome: | The proposed method improves on a dataset of 12 Indian languages . it also improves quality of the extracted cognates by up to 2.76 BLEU . |
Probing for Referential Information in Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Neural network-based language models (LMs) have been shown to learn relevant properties of language without being explicitly trained for them. |
| Approach: | They extend their previous work to analyze whether language models capture anaphoric relations and pronoun-antecedent relations in English. |
| Outcome: | The Transformer outperforms the LSTM in all analyses. |
Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing studies show that multilingual pre-trained models can learn to generalise across languages . however, it remains unclear how these models learn to learn multilingual representations . |
| Approach: | They propose a hypothesis that multilingual pre-trained models can derive language-universal abstractions about grammar by aligning morphosyntactic markers that fulfil a similar grammatical function across languages. |
| Outcome: | The proposed model can derive language-universal abstractions even without explicit supervision. |
Lexicosyntactic Inference in Neural Models (D18-1)
Copied to clipboard
| Challenge: | lexicosyntactic inferences are triggered by surprising aspects of the syntactical context that a word occurs in. |
| Approach: | They build a factuality judgment dataset for English clause-embedding verbs in various syntactic contexts and use it to probe the behavior of current state-of-the-art neural systems. |
| Outcome: | The proposed model makes systematic errors that are visible through the lens of factuality prediction. |
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? (2021.eacl-main)
Copied to clipboard
| Challenge: | Neural models have established state-of-the-art performance on several NLP benchmarks, but little is understood about the mechanisms by which they operate. |
| Approach: | They examine the probing paradigm through a set of controlled synthetic tasks and show that pretrained word embeddings play a considerable role in encoding these properties rather than the training task itself. |
| Outcome: | The proposed model can encode linguistic properties above chance-level even when distributed in the data as random noise, reversing the interpretation of absolute claims on probing tasks. |
A Study on Accessing Linguistic Information in Pre-Trained Language Models by Using Prompts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to access linguistic information in pre-trained multilingual language models are difficult to use. |
| Approach: | They propose prompting and formulate linguistic tasks to test the LM's access to explicit grammar principles and find out what type of information can be obtained . |
| Outcome: | The proposed method can provide access to linguistic features in pre-trained models, but some are harder to capture . |
Can Cognate Prediction Be Modelled as a Low-Resource Machine Translation Task? (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on cognate prediction based on similarities of two languages has not studied their differences or optimized architectural choices. |
| Approach: | They compare statistical and neural MT architectures to a bilingual setup to test their hypothesis . they use monolingual pretraining, backtranslation and multilinguality to test the hypothesis based on the results . |
| Outcome: | The proposed architectures can be used to generate cognates in a given language . the proposed architecture can be employed with monolingual pretraining, backtranslation and multilinguality . |
How Reliable are Model Diagnostics? (2021.findings-acl)
Copied to clipboard
| Challenge: | Contemporary statistical models trade off interpretability and simplicity for powerful parameterizations and inductive biases, enabling impressive performance. |
| Approach: | They examine three recent models and find they are not yet reliable . they also formulate recommendations for practitioners and researchers . |
| Outcome: | The proposed models are not as reliable as previously assumed, the authors argue . their findings suggest that they are needed for improving models and training setups . |
Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics? (N18-2)
Copied to clipboard
| Challenge: | Phylogenetic trees are hypotheses of how sets of related languages evolved in time. |
| Approach: | They compare the performance of automatic cognate detection algorithms to classical manually annotated cognate sets. |
| Outcome: | The proposed methods perform better than classically annotated cognate sets . future work on phylogenetic reconstruction can profit from the results . |