Lluís Màrquez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lluís Màrquez has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Preslav Nakov
Mohamed bin Zayed University of Artificial Intelligence
6 shared publications - Francisco Guzmán
Facebook AI
3 shared publications - Francisco Guzmán
Arabic Language Technologies Research Group Qatar Computing Research Institute HBKU
2 shared publications - Shafiq Joty
ALT Research Group Qatar Computing Research Institute -Qatar Foundation
2 shared publications Alberto Barrón-Cedeño
Qatar Computing Research Institute HBKU
1 shared publication- Alberto Barrón-Cedeño
DIT, Università di Bologna, Forlì, Italy
1 shared publication
Latest Publications
- Open Access
Machine Translation Evaluation Meets Community Question Answering
We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.
Open AccessMachine Translation Evaluation Meets Community Question Answering
We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.
- Open Access
DiscoTK: Using Discourse Structure for Machine Translation Evaluation
We present novel automatic metrics for machine translation evaluation that use discourse structure and convolution kernels to compare the discourse tree of an automatic translation with that of the human reference. We experiment with five transformations and augmentations of a base discourse tree representation based on the rhetorical structure theory, and we combine the kernel scores for each of them into a single score. Finally, we add other metrics from the ASIYA MT evaluation toolkit, and we tune the weights of the combination on actual human judgments. Experiments on the WMT12 and WMT13 metrics shared task datasets show correlation with human judgments that outperforms what the best systems that participated in these years achieved, both at the segment and at the system level.
Open AccessDiscoTK: Using Discourse Structure for Machine Translation Evaluation
We present novel automatic metrics for machine translation evaluation that use discourse structure and convolution kernels to compare the discourse tree of an automatic translation with that of the human reference. We experiment with five transformations and augmentations of a base discourse tree representation based on the rhetorical structure theory, and we combine the kernel scores for each of them into a single score. Finally, we add other metrics from the ASIYA MT evaluation toolkit, and we tune the weights of the combination on actual human judgments. Experiments on the WMT12 and WMT13 metrics shared task datasets show correlation with human judgments that outperforms what the best systems that participated in these years achieved, both at the segment and at the system level.
- Open Access
Global Thread-Level Inference for Comment Classification in Community Question Answering
Community question answering, a recent evolution of question answering in the Web context, allows a user to quickly consult the opinion of a number of people on a particular topic, thus taking advantage of the wisdom of the crowd. Here we try to help the user by deciding automatically which answers are good and which are bad for a given question. In particular, we focus on exploiting the output structure at the thread level in order to make more consistent global decisions. More specifically, we exploit the relations between pairs of comments at any distance in the thread, which we incorporate in a graph-cut and in an ILP frameworks. We evaluated our approach on the benchmark dataset of SemEval-2015 Task 3. Results improved over the state of the art, confirming the importance of using thread level information.
Open AccessGlobal Thread-Level Inference for Comment Classification in Community Question Answering
Community question answering, a recent evolution of question answering in the Web context, allows a user to quickly consult the opinion of a number of people on a particular topic, thus taking advantage of the wisdom of the crowd. Here we try to help the user by deciding automatically which answers are good and which are bad for a given question. In particular, we focus on exploiting the output structure at the thread level in order to make more consistent global decisions. More specifically, we exploit the relations between pairs of comments at any distance in the thread, which we incorporate in a graph-cut and in an ILP frameworks. We evaluated our approach on the benchmark dataset of SemEval-2015 Task 3. Results improved over the state of the art, confirming the importance of using thread level information.
- Open Access
Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the trained models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the classifier as a proxy to the quality of the original NMT model for the given task. Our quantitative analysis yields interesting insights regarding representation learning in NMT models. For instance, we find that higher layers are better at learning semantics while lower layers tend to be better for part-of-speech tagging. We also observe little effect of the target language on source-side representations, especially with higher quality NMT models.
Open AccessEvaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks
While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the trained models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the classifier as a proxy to the quality of the original NMT model for the given task. Our quantitative analysis yields interesting insights regarding representation learning in NMT models. For instance, we find that higher layers are better at learning semantics while lower layers tend to be better for part-of-speech tagging. We also observe little effect of the target language on source-side representations, especially with higher quality NMT models.
- Open Access
- 1 December 2017
- Published by MIT Press in Computational Linguistics
- Vol. 43 (4) , 683-722
Discourse Structure in Machine Translation Evaluation
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory (RST). Then, we show that a simple linear combination with these measures can help improve various existing machine translation evaluation metrics regarding correlation with human judgments both at the segment level and at the system level. This suggests that discourse information is complementary to the information used by many of the existing evaluation metrics, and thus it could be taken into account when developing richer evaluation metrics, such as the WMT-14 winning combined metric DiscoTKparty. We also provide a detailed analysis of the relevance of various discourse elements and relations from the RST parse trees for machine translation evaluation. In particular, we show that (i) all aspects of the RST tree are relevant, (ii) nuclearity is more useful than relation type, and (iii) the similarity of the translation RST tree to the reference RST tree is positively correlated with translation quality.
- 1 December 2017
- Published by MIT Press in Computational Linguistics
- Vol. 43 (4) , 683-722
Open AccessDiscourse Structure in Machine Translation Evaluation
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory (RST). Then, we show that a simple linear combination with these measures can help improve various existing machine translation evaluation metrics regarding correlation with human judgments both at the segment level and at the system level. This suggests that discourse information is complementary to the information used by many of the existing evaluation metrics, and thus it could be taken into account when developing richer evaluation metrics, such as the WMT-14 winning combined metric DiscoTKparty. We also provide a detailed analysis of the relevance of various discourse elements and relations from the RST parse trees for machine translation evaluation. In particular, we show that (i) all aspects of the RST tree are relevant, (ii) nuclearity is more useful than relation type, and (iii) the similarity of the translation RST tree to the reference RST tree is positively correlated with translation quality.
- 1 September 2017
- Published by Elsevier in Computer Speech & Language
- Vol. 45, 180-200
Machine translation evaluation with neural networks
- 1 September 2017
- Published by Elsevier in Computer Speech & Language
- Vol. 45, 180-200
Machine translation evaluation with neural networks
- Open Access
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
It Takes Three to Tango: Triangulation Approach to Answer Ranking in Community Question Answering
- 1 January 2016
- Published by Association for Computational Linguistics (ACL)
Open AccessIt Takes Three to Tango: Triangulation Approach to Answer Ranking in Community Question Answering
- 28 September 2015
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 54, 159-192
Leveraging Online User Feedback to Improve Statistical Machine Translation
- 28 September 2015
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 54, 159-192
Leveraging Online User Feedback to Improve Statistical Machine Translation
- 16 September 2014
- Published by Springer Nature in Machine Translation
- Vol. 28 (2) , 91-125
A hybrid machine translation architecture guided by syntax
- 16 September 2014
- Published by Springer Nature in Machine Translation
- Vol. 28 (2) , 91-125
A hybrid machine translation architecture guided by syntax