A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2009; you can also visit the original URL.
The file type is application/pdf.
Filters
Why generative phrase models underperform surface heuristics
2006
Proceedings of the Workshop on Statistical Machine Translation - StatMT '06
unpublished
Preserved Fulltext
We investigate why weights from generative models underperform heuristic estimates in phrasebased machine translation. ...
We first propose a simple generative, phrase-based model and verify that its estimates are inferior to those given by surface statistics. ...
One particularly surprising result is that a simple heuristic extraction algorithm based on surface statistics of a word-aligned training set outperformed the phrase-based generative model proposed by ...
doi:10.3115/1654650.1654656
fatcat:qo5f3zarm5bnfajzesp765by6m
Abstractive Summarization: A Survey of the State of the Art
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Originally developed for machine translation, neural methods provide a viable framework for obtaining an abstract representation of the meaning of an input text and generating informative, fluent, and ...
This could explain why extractive summarizers underperform the RLbased abstractive summarizers: RL can address an abstractive summarizer's weakness in making sentence-level decisions. ...
Surface realization Surface realization aims to combine the candidates selected in content selection using grammatical/syntactic rules to generate a summary. ...
doi:10.1609/aaai.v33i01.33019815
fatcat:ufoyvxeuundelfoul5kzbjeutq
DSCo-NG: A Practical Language Modeling Approach for Time Series Classification
[chapter]
2016
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Our previous work, Domain Series Corpus (DSCo), compresses time series into symbolic strings and takes advantage of language modeling techniques to extract from the training set knowledge about different ...
propose DSCo-NG, which reduces DSCo's complexity and offers an efficient (linear time complexity and low memory footprint), accurate (performance comparable to approaches working on uncompressed data) and generic ...
This is a major reason why DSCo-NG greatly underperforms 1NN for the WordSynonyms dataset, which has many (25) classes but very few (267) training instances. ...
doi:10.1007/978-3-319-46349-0_1
fatcat:r74kcumiifhrlph3rrge4qqt7y
Generative Models can Help Writers without Writing for Them
2021
International Conference on Intelligent User Interfaces
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Computational models of language have the exciting potential to help writers generate and express their ideas. ...
We present early explorations of two new types of interactions with generative language models; both share the design goal of keeping the writer in ultimate control while providing generative assistance ...
We are grateful to the contributors to the Huggingface Transformers project, especially the Helsinki NLP group, for making easy-to-use APIs for pre-trained models. ...
dblp:conf/iui/ArnoldVM21
fatcat:ydzrb7rrvvaczbd2ajbw26t37a
Statistical Deep Parsing for Spanish: Abridged Version
2022
CLEI Electronic Journal
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
HPSG is a deep linguistic formalism that combines syntactic and semantic information in the same representation, and is capable of elegantly modeling many linguistic phenomena. ...
The rather weak statistical model, than only takes in consideration partial information from the supertags, might be one reason why these models are underperforming. ...
It is possible that many valid trees are generated in the process, so we also need a probabilistic model for determining which of the trees is the most likely one. ...
doi:10.19153/cleiej.25.1.2
fatcat:k5jdrcbqcjc5vccmw5x4egckke
Linguistically Annotated Reordering: Evaluation and Analysis
2010
Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
system translations, and summarize syntactic reordering patterns that are captured by reordering models. ...
Linguistic knowledge plays an important role in phrase movement in statistical machine translation. ...
If it is not necessary, do the heuristic selection rules impose any bias on
the reordering model? ...
doi:10.1162/coli_a_00009
fatcat:kzn6ydkakzecparatgjgtcnyfq
A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena
2016
Computational Linguistics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Other Versions
advanced reordering modeling. ...
We then question why some approaches are more successful than others in different language pairs. ...
Model type indicates whether a model is trained in a generative (gener.) or discriminative (discr.) way. ...
doi:10.1162/coli_a_00245
fatcat:bgq57yklijgllhn42trnobaexa
Latent Relation Language Models
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose Latent Relation Language Models (LRLMs), a class of language models that parameterizes the joint distribution over the words in a document and the entities that occur therein ...
This model has a number of attractive properties: it not only improves language modeling performance, but is also able to annotate the posterior probability of entity spans for a given text through relations ...
However, our model often favors word-based generation for common phrases even if related entities exist. ...
doi:10.1609/aaai.v34i05.6298
fatcat:zkcvm3b7tnarng7dy4bghyhyim
NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
As a first step toward the latter, this paper proposes NegatER, a framework that ranks potential negatives in commonsense KBs using a contextual language model (LM). ...
, coherent, and informative -- leading to statistically significant accuracy improvements in a challenging KB completion task and confirming that the positive knowledge in LMs can be "re-purposed" to generate ...
To make COMET generate negatives, we prepend a "not" token to each positive head phrase X + h and generate 10 tail phrases X COMET t for the modified head/relation prefix using beam search. ...
arXiv:2011.07497v2
fatcat:g6evjmoeu5cvdgw2m6rnu636bu
Reconnecting interpretation to reasoning through individual differences
2006
Quarterly Journal of Experimental Psychology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is application/pdf.
Grice's theory taken as a broad framework for credulous discourse processing in which participants construct speakers' "intended models" of discourses can reconcile these results, purchasing continuity ...
We conclude that most participants do not understand deductive tasks as experimenters intend, and just as there is no single logical model of reasoning, so there is no reason to expect a single "fundamental ...
In the exceptional problem where the source identified by the heuristic cannot be so used, they underperform their peers on the canonically ordered problem but outperform them on the noncanonical member ...
doi:10.1080/17470210500198759
pmid:16846971
fatcat:mgf4beid5bfrlo3gkn56ws6gdq
Getting Past the Language Gap: Innovations in Machine Translation
[chapter]
2012
Mobile Speech and Advanced Natural Language Solutions
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Translation Models and the Problem of Overfitting It is possible to distinguish between generative translation models (essentially, the IBM models), and the other half to various discriminative models. ...
The authors take into consideration the "collocation"-like ability of adjacent words to appear in a phrase. Different phrase segmentation will generate different translation results. ...
The model is also capable of estimating phrase correspondences automatically without heuristic rules. ...
doi:10.1007/978-1-4614-6018-3_6
fatcat:2njkc6meabhaxosl4wircumfjm
Précis of Simple heuristics that make us smart
2000
Behavioral and Brain Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
These simple heuristics perform comparably to more complex algorithms, particularly when generalizing to new data -that is, simplicity leads to robustness. ...
decision making for choice, elimination models for categorization, and satisficing heuristics for sequential search. ...
Why and when do simple heuristics work? ...
doi:10.1017/s0140525x00003447
fatcat:43gpji75ifbv3jej4n2xef25vi
Précis of Simple heuristics that make us smart
2000
Behavioral and Brain Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
decision making for choice, elimination models for categorization, and satisficing heuristics for sequential search. ...
These simple heuristics perform comparably to more complex algorithms, particularly when generalizing to new data--that is, simplicity leads to robustness. ...
Even in the cases they describe, the models often seriously underperform other models such as a neural network (Table 11-1 ). ...
pmid:11301545
fatcat:2rcestruqzeurjcgbvj2akmfbm
Unsupervised Sub-tree Alignment for Tree-to-Tree Translation
2013
The Journal of Artificial Intelligence Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Unlike previous work, we do not resort to surface heuristics or expensive annotated data, but instead derive an unsupervised model to infer the syntactic correspondence between two languages. ...
With tree binarization and fuzzy decoding, it even outperforms a state-of-the-art hierarchical phrase-based system. ...
We attribute this to the better use of syntactic information on both language sides in our model, which are generally ignored in traditional models based on surface heuristics and word alignments. ...
doi:10.1613/jair.4033
fatcat:tvkuj36omvdivkbstmnmdcxc4u
The NarrativeQA Reading Comprehension Challenge
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We show that although humans solve the tasks easily, standard RC models struggle on the tasks presented here. We provide an analysis of the dataset and the challenges it presents. ...
The data is human generated, and the answers can be phrases or sentences. ...
While the answers are multiword phrases, the spans are generally short and rarely cross sentence boundaries. ...
arXiv:1712.07040v1
fatcat:4vjf4yx6f5gadjpynnxb2mrp5y
« Previous
Showing results 1 — 15 out of 402 results