One Source, Two Targets: Challenges and Rewards of Dual Decoding

Fran\c{c}ois Yvon; Jitao Xu

RECORD

One Source, Two Targets: Challenges and Rewards of Dual Decoding

Jitao Xu, François Yvon

Computation and Language · Submitted 21 Sep 2021

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim Viewing the problem from multiple angles allows us to better highlight the challenges of dual decoding and to also thoroughly analyze the benefits of generating matched, rather than independent, translations.

how it is stated · asserted 0.90 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,168 input tokens.

What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.23 · human participants 0.06 · controlled comparison 0.13 · randomized assignment 0.01 · states quantitative result 0.17 · compares with prior results 0.10 · mentions code or data availability 0.03.

The abstract, sentence by sentence

arXiv listing abstract v1. Results and the main claim are underlined; show every role.

Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other. As we discuss, such a device serves several practical purposes, from multi-target machine translation to the generation of controlled variations of the target text. We present an analysis of possible implementations of dual decoding, and experiment with four applications. Viewing the problem from multiple angles allows us to better highlight the challenges of dual decoding and to also thoroughly analyze the benefits of generating matched, rather than independent, translations.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	Machine translation is generally understood as generating one target text from an input source document.	background 1.00	0.03	0.02	asserted 0.92
s1	In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other.	contribution 0.92	0.34	0.08	asserted 0.90
s2	As we discuss, such a device serves several practical purposes, from multi-target machine translation to the generation of controlled variations of the target text.	background 0.47	0.16	0.08	asserted 0.82
s3	We present an analysis of possible implementations of dual decoding, and experiment with four applications.	contribution 0.98	0.95	0.06	asserted 0.96
s4	Viewing the problem from multiple angles allows us to better highlight the challenges of dual decoding and to also thoroughly analyze the benefits of generating matched, rather than independent, translations.	contribution 0.63	0.82	0.29	asserted 0.90

What kind of paper the classifier reports this is: empirical study 0.71 · evidence from observation or experiment 0.97.

What was examined, and what was not

sources read

arXiv listing abstract v1

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other. As we discuss, such a device serves several practical purposes, from multi-target machine translation to the generation of controlled variations of the target text. We present an analysis of possible implementations of dual decoding, and experiment with four applications. Viewing the problem from multiple angles allows us to better highlight the challenges of dual decoding and to also thoroughly analyze the benefits of generating matched, rather than independent, translations.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

What this paper does with the arXiv papers it cites

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

What it cites

Cites as background 2 papers

Since the introduction of the first encoder-decoder architecture [ref] , then completed with an attention mechanism [ref] , the performance of NMT systems is now good enough for a growing number of services, both for the general public and the translation industry.

Neural Machine Translation by Jointly Learning to Align and Translate · Introduction · 1.00
Code-switching is an important linguistic phenomenon in bilingual communities that is getting momentum within the natural language processing communities [ref] .

A Survey of Code-switched Speech and Language Processing · Related Work · 0.97

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.