Paper Group NANR 92
Examining MDD and MHD as Syntactic Complexity Measures with Intermediate Japanese Learner Corpus Data. Which annotation scheme is more expedient to measure syntactic difficulty and cognitive demand?. Advantages of the flux-based interpretation of dependency length minimization. Extracting out of the subject in French: experimental evidence. Towards …
Examining MDD and MHD as Syntactic Complexity Measures with Intermediate Japanese Learner Corpus Data
| Title | Examining MDD and MHD as Syntactic Complexity Measures with Intermediate Japanese Learner Corpus Data |
| Authors | Saeko Komori, Masatoshi Sugiura, Wenping Li |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7715/ |
| https://www.aclweb.org/anthology/W19-7715 | |
| PWC | https://paperswithcode.com/paper/examining-mdd-and-mhd-as-syntactic-complexity |
| Repo | |
| Framework | |
Which annotation scheme is more expedient to measure syntactic difficulty and cognitive demand?
| Title | Which annotation scheme is more expedient to measure syntactic difficulty and cognitive demand? |
| Authors | Jianwei Yan, Haitao Liu |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7903/ |
| https://www.aclweb.org/anthology/W19-7903 | |
| PWC | https://paperswithcode.com/paper/which-annotation-scheme-is-more-expedient-to |
| Repo | |
| Framework | |
Advantages of the flux-based interpretation of dependency length minimization
| Title | Advantages of the flux-based interpretation of dependency length minimization |
| Authors | Sylvain Kahane, Chunxiao Yan |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7912/ |
| https://www.aclweb.org/anthology/W19-7912 | |
| PWC | https://paperswithcode.com/paper/advantages-of-the-flux-based-interpretation |
| Repo | |
| Framework | |
Extracting out of the subject in French: experimental evidence
| Title | Extracting out of the subject in French: experimental evidence |
| Authors | Anne Abeill{'e}, Elodie Winckel |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7908/ |
| https://www.aclweb.org/anthology/W19-7908 | |
| PWC | https://paperswithcode.com/paper/extracting-out-of-the-subject-in-french |
| Repo | |
| Framework | |
Towards an adequate account of parataxis in Universal Dependencies
| Title | Towards an adequate account of parataxis in Universal Dependencies |
| Authors | Lars Ahrenberg |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-8011/ |
| https://www.aclweb.org/anthology/W19-8011 | |
| PWC | https://paperswithcode.com/paper/towards-an-adequate-account-of-parataxis-in |
| Repo | |
| Framework | |
Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction
| Title | Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction |
| Authors | Lifeng Jin, William Schuler |
| Abstract | In unsupervised grammar induction, data likelihood is known to be only weakly correlated with parsing accuracy, especially at convergence after multiple runs. In order to find a better indicator for quality of induced grammars, this paper correlates several linguistically- and psycholinguistically-motivated predictors to parsing accuracy on a large multilingual grammar induction evaluation data set. Results show that variance of average surprisal (VAS) better correlates with parsing accuracy than data likelihood and that using VAS instead of data likelihood for model selection provides a significant accuracy boost. Further evidence shows VAS to be a better candidate than data likelihood for predicting word order typology classification. Analyses show that VAS seems to separate content words from function words in natural language grammars, and to better arrange words with different frequencies into separate classes that are more consistent with linguistic theory. |
| Tasks | Model Selection |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1235/ |
| https://www.aclweb.org/anthology/P19-1235 | |
| PWC | https://paperswithcode.com/paper/variance-of-average-surprisal-a-better |
| Repo | |
| Framework | |
Towards transferring Bulgarian Sentences with Elliptical Elements to Universal Dependencies: issues and strategies
| Title | Towards transferring Bulgarian Sentences with Elliptical Elements to Universal Dependencies: issues and strategies |
| Authors | Petya Osenova, Kiril Simov |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-8014/ |
| https://www.aclweb.org/anthology/W19-8014 | |
| PWC | https://paperswithcode.com/paper/towards-transferring-bulgarian-sentences-with |
| Repo | |
| Framework | |
Mapping the hyponymy relation of wordnet onto vector Spaces
| Title | Mapping the hyponymy relation of wordnet onto vector Spaces |
| Authors | Jean-Philippe Bernardy, Aleksandre Maskharashvili |
| Abstract | In this paper, we investigate mapping the hyponymy relation of wordnet to feature vectors. We aim to model lexical knowledge in such a way that it can be used as input in generic machine-learning models, such as phrase entailment predictors. We propose two models. The first one leverages an existing mapping of words to feature vectors (fasttext), and attempts to classify such vectors as within or outside of each class. The second model is fully supervised, using solely wordnet as a ground truth. It maps each concept to an interval or a disjunction thereof. On the first model, we approach, but not quite attain state of the art performance. The second model can achieve near-perfect accuracy. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1xywsC9tQ |
| https://openreview.net/pdf?id=r1xywsC9tQ | |
| PWC | https://paperswithcode.com/paper/mapping-the-hyponymy-relation-of-wordnet-onto |
| Repo | |
| Framework | |
Semantic Modelling of Adjective-Noun Collocations Using FrameNet
| Title | Semantic Modelling of Adjective-Noun Collocations Using FrameNet |
| Authors | Yana Strakatova, Erhard Hinrichs |
| Abstract | In this paper we argue that Frame Semantics (Fillmore, 1982) provides a good framework for semantic modelling of adjective-noun collocations. More specifically, the notion of a frame is rich enough to account for nouns from different semantic classes and to model semantic relations that hold between an adjective and a noun in terms of Frame Elements. We have substantiated these findings by considering a sample of adjective-noun collocations from German such as {}enger Freund{''} {`}close friend{'} and {}starker Regen{''} {`}heavy rain{'}. The data sample is taken from different semantic fields identified in the German wordnet GermaNet (Hamp and Feldweg, 1997; Henrich and Hinrichs, 2010). The study is based on the electronic dictionary DWDS (Klein and Geyken, 2010) and uses the collocation extraction tool Wortprofil (Geyken et al., 2009). The FrameNet modelling is based on the online resource available at http://framenet.icsi.berkeley.edu. Since FrameNets are available for a range of typologically different languages, it is feasible to extend the current case study to other languages. | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5112/ |
| https://www.aclweb.org/anthology/W19-5112 | |
| PWC | https://paperswithcode.com/paper/semantic-modelling-of-adjective-noun |
| Repo | |
| Framework | |
Enhancing Phrase-Based Statistical Machine Translation by Learning Phrase Representations Using Long Short-Term Memory Network
| Title | Enhancing Phrase-Based Statistical Machine Translation by Learning Phrase Representations Using Long Short-Term Memory Network |
| Authors | Benyamin Ahmadnia, Bonnie Dorr |
| Abstract | Phrases play a key role in Machine Translation (MT). In this paper, we apply a Long Short-Term Memory (LSTM) model over conventional Phrase-Based Statistical MT (PBSMT). The core idea is to use an LSTM encoder-decoder to score the phrase table generated by the PBSMT decoder. Given a source sequence, the encoder and decoder are jointly trained in order to maximize the conditional probability of a target sequence. Analytically, the performance of a PBSMT system is enhanced by using the conditional probabilities of phrase pairs computed by an LSTM encoder-decoder as an additional feature in the existing log-linear model. We compare the performance of the phrase tables in the PBSMT to the performance of the proposed LSTM and observe its positive impact on translation quality. We construct a PBSMT model using the Moses decoder and enrich the Language Model (LM) utilizing an external dataset. We then rank the phrase tables using an LSTM-based encoder-decoder. This method produces a gain of up to 3.14 BLEU score on the test set. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1004/ |
| https://www.aclweb.org/anthology/R19-1004 | |
| PWC | https://paperswithcode.com/paper/enhancing-phrase-based-statistical-machine |
| Repo | |
| Framework | |
Posterior Attention Models for Sequence to Sequence Learning
| Title | Posterior Attention Models for Sequence to Sequence Learning |
| Authors | Shiv Shankar, Sunita Sarawagi |
| Abstract | Modern neural architectures critically rely on attention for mapping structured inputs to sequences. In this paper we show that prevalent attention architectures do not adequately model the dependence among the attention and output variables along the length of a predicted sequence. We present an alternative architecture called Posterior Attention Models that relying on a principled factorization of the full joint distribution of the attention and output variables propose two major changes. First, the position where attention is marginalized is changed from the input to the output. Second, the attention propagated to the next decoding stage is a posterior attention distribution conditioned on the output. Empirically on five translation and two morphological inflection tasks the proposed posterior attention models yield better predictions and alignment accuracy than existing attention models. |
| Tasks | Morphological Inflection |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BkltNhC9FX |
| https://openreview.net/pdf?id=BkltNhC9FX | |
| PWC | https://paperswithcode.com/paper/posterior-attention-models-for-sequence-to |
| Repo | |
| Framework | |
Enhanced Transformer Model for Data-to-Text Generation
| Title | Enhanced Transformer Model for Data-to-Text Generation |
| Authors | Li Gong, Josep Crego, Jean Senellart |
| Abstract | Neural models have recently shown significant progress on data-to-text generation tasks in which descriptive texts are generated conditioned on database records. In this work, we present a new Transformer-based data-to-text generation model which learns content selection and summary generation in an end-to-end fashion. We introduce two extensions to the baseline transformer model: First, we modify the latent representation of the input, which helps to significantly improve the content correctness of the output summary; Second, we include an additional learning objective that accounts for content selection modelling. In addition, we propose two data augmentation methods that succeed to further improve performance of the resulting generation models. Evaluation experiments show that our final model outperforms current state-of-the-art systems as measured by different metrics: BLEU, content selection precision and content ordering. We made publicly available the transformer extension presented in this paper. |
| Tasks | Data Augmentation, Data-to-Text Generation, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5615/ |
| https://www.aclweb.org/anthology/D19-5615 | |
| PWC | https://paperswithcode.com/paper/enhanced-transformer-model-for-data-to-text |
| Repo | |
| Framework | |
Weakly deterministic transformations are subregular
| Title | Weakly deterministic transformations are subregular |
| Authors | Andrew Lamont, Charlie O{'}Hara, Caitlin Smith |
| Abstract | Whether phonological transformations in general are subregular is an open question. This is the case for most transformations, which have been shown to be subsequential, but it is not known whether weakly deterministic mappings form a proper subset of the regular functions. This paper demonstrates that there are regular functions that are not weakly deterministic, and, because all attested processes are weakly deterministic, supports the subregular hypothesis. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4223/ |
| https://www.aclweb.org/anthology/W19-4223 | |
| PWC | https://paperswithcode.com/paper/weakly-deterministic-transformations-are |
| Repo | |
| Framework | |
Automatic Propbank Generation for Turkish
| Title | Automatic Propbank Generation for Turkish |
| Authors | Koray AK, Olcay Taner Y{\i}ld{\i}z |
| Abstract | Semantic role labeling (SRL) is an important task for understanding natural languages, where the objective is to analyse propositions expressed by the verb and to identify each word that bears a semantic role. It provides an extensive dataset to enhance NLP applications such as information retrieval, machine translation, information extraction, and question answering. However, creating SRL models are difficult. Even in some languages, it is infeasible to create SRL models that have predicate-argument structure due to lack of linguistic resources. In this paper, we present our method to create an automatic Turkish PropBank by exploiting parallel data from the translated sentences of English PropBank. Experiments show that our method gives promising results. |
| Tasks | Information Retrieval, Machine Translation, Question Answering, Semantic Role Labeling |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1005/ |
| https://www.aclweb.org/anthology/R19-1005 | |
| PWC | https://paperswithcode.com/paper/automatic-propbank-generation-for-turkish |
| Repo | |
| Framework | |
IDION: A database for Modern Greek multiword expressions
| Title | IDION: A database for Modern Greek multiword expressions |
| Authors | Stella Markantonatou, Panagiotis Minos, George Zakis, Vassiliki Moutzouri, Maria Chantou |
| Abstract | We report on the ongoing development of IDION, a web resource of richly documented multiword expressions (MWEs) of Modern Greek addressed to the human user and to NLP. IDION contains about 2000 verb MWEs (VMWEs) of which about 850 are fully documented as regards their syntactic flexibility, their semantics and the semantic relations with other VMWEs. Sets of synonymous MWEs are defined in a bottom-up manner revealing the conceptual organization of the MG VMWE domain. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5115/ |
| https://www.aclweb.org/anthology/W19-5115 | |
| PWC | https://paperswithcode.com/paper/idion-a-database-for-modern-greek-multiword |
| Repo | |
| Framework | |
