User
la frase "il topo è inseguito dal gatto" è attiva o passiva?

ChatGPT
La frase "il topo è inseguito dal gatto" è in forma passiva.

User
come fai a saperlo?

ChatGPT
Posso determinare che la frase "il topo è inseguito dal gatto" è in forma
passiva seguendo alcune caratteristiche grammaticali tipiche delle frasi
passive in italiano:
    Struttura della frase: Nelle frasi passive, il soggetto riceve l'azione
piuttosto che eseguirla. Nell'esempio fornito, il topo (soggetto) riceve
l'azione di essere inseguito.
    Verbo: La frase utilizza una forma del verbo "essere" seguita dal
participio passato del verbo principale. In questo caso, "è inseguito".
    Agente della passiva: Nelle frasi passive, l'entità che esegue l'azione
è spesso introdotta dalla preposizione "da". In questo esempio, l'agente
dell'azione è "il gatto", e viene introdotto appunto con "dal".
Combinando queste caratteristiche, è chiaro che la frase è in forma passiva.

User
per determinare la forma di una frase, tu applichi esattamente le regole
che hai appena elencato?

ChatGPT
No, non utilizzo una lista di regole in modo rigido e sequenziale come
potrebbe fare un algoritmo tradizionale di elaborazione del linguaggio.
Invece, il mio modello è basato su una vasta quantità di dati testuali che
ho analizzato durante la mia formazione. Quando "valuto" una frase,
riconosco schemi e strutture linguistiche basati su quel vasto corpus di
dati.
Tuttavia, quando ti ho fornito quelle caratteristiche grammaticali, ho
voluto spiegare in modo esplicito e comprensibile come si può riconoscere
una frase passiva in italiano. Era un modo per fornirti una spiegazione
chiara e didattica. Nel "pensiero" interno del modello, la determinazione
avviene in maniera molto più fluida e basata sul riconoscimento di schemi
nei dati.



Per ora è tutto, a voi la linea :-)

G.

On Sun, 15 Oct 2023 at 20:21, 380° <g...@biscuolo.net> wrote:

> Buonasera,
>
> Giuseppe Attardi <atta...@di.unipi.it> writes:
>
> > C’è tutta un’area di ricerca, che passa sotto il nome di BERTology,
> > che analizza la questione e si dimostra ad esempio che dalle relazioni
> > presenti nella matrici di attention delle frasi, si può ricavare
> > l’intero albero sintattico della frase:
> > https://aclanthology.org/N19-1419.pdf
>
> «A Structural Probe for Finding Syntax in Word Representations»
> John Hewitt, Christopher D. Manning
> Published 1 June 2019
> (via
>
> https://www.semanticscholar.org/paper/A-Structural-Probe-for-Finding-Syntax-in-Word-Hewitt-Manning/455a8838cde44f288d456d01c76ede95b56dc675
> )
>
> --8<---------------cut here---------------start------------->8---
>
> Recent work has improved our ability to detect linguistic knowledge in
> word representations. However, current methods for detecting syntactic
> knowledge do not test whether syntax trees are represented in their
> entirety. In this work, we propose a structural probe, which evaluates
> whether syntax trees are embedded in a linear transformation of a neural
> network’s word representation space. The probe identifies a linear
> transformation under which squared L2 distance encodes the distance
> between words in the parse tree, and one in which squared L2 norm
> encodes depth in the parse tree. Using our probe, we show that such
> transformations exist for both ELMo and BERT but not in baselines,
> providing evidence that entire syntax trees are embedded implicitly in
> deep models’ vector geometry.
>
> --8<---------------cut here---------------end--------------->8---
>
> Interessante, ma se davvero vogliamo parlare di BERTology allora, ripeto
> [1] che nel Vol. 8 del Transactions of the Association for Computational
> Linguistics del MIT (2020) è pubblicato questo articolo:
>
> «A Primer in BERTology: What We Know About How BERT Works»
> by Anna Rogers, Olga Kovaleva, Anna Rumshisky
>
>
> https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00349/96482/A-Primer-in-BERTology-What-We-Know-About-How-BERT
>
> che cita il paper sopra tra le fonti per descrivere le caratteristiche
> di syntactic knowledge di BERT, mentre più avanti, nel capitolo "3.3
> World Knowledge" e "3.4 Limitations" scrive:
>
> --8<---------------cut here---------------start------------->8---
>
> However, BERT cannot reason based on its world knowledge. Forbes et
> al. (2019) show that BERT can “guess” the affordances and properties of
> many objects, but cannot reason about the relationship between
> properties and affordances. For example, it “knows” that people can walk
> into houses, and that houses are big, but it cannot infer that houses
> are bigger than people. Zhou et al. (2020) and Richardson and Sabharwal
> (2019) also show that the performance drops with the number of necessary
> inference steps. Some of BERT’s world knowledge success comes from
> learning stereotypical associations (Poerner et al., 2019), for example,
> a person with an Italian-sounding name is predicted to be Italian, even
> when it is incorrect.
>
> 3.4 Limitations
>
> Multiple probing studies in section 3 and section 4 report that BERT
> possesses a surprising amount of syntactic, semantic, and world
> knowledge. However, Tenney et al. (2019a) remark, “the fact that a
> linguistic pattern is not observed by our probing classifier does not
> guarantee that it is not there, and the observation of a pattern does
> not tell us how it is used.” There is also the issue of how complex a
> probe should be allowed to be (Liu et al., 2019a). If a more complex
> probe recovers more information, to what extent are we still relying on
> the original model?
>
> Furthermore, different probing methods may lead to complementary or even
> contradictory conclusions, which makes a single test (as in most
> studies) insufficient (Warstadt et al., 2019). A given method might also
> favor one model over another, for example, RoBERTa trails BERT with one
> tree extraction method, but leads with another (Htut et al., 2019). The
> choice of linguistic formalism also matters (Kuznetsov and Gurevych,
> 2020).
>
> [...]
>
> --8<---------------cut here---------------end--------------->8---
>
> Nel 2020 i ricercatori citati sopra sostenevano che BERT non è in grado
> di ragionare.
>
> Sullo stesso numero della rivista è pubblicato anche questo articolo:
>
> «What BERT Is Not: Lessons from a New Suite of Psycholinguistic
> Diagnostics for Language Models»
> by Allyson Ettinger
>
>
> https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00298/43535/What-BERT-Is-Not-Lessons-from-a-New-Suite-of
>
> cito dalle conclusioni:
>
> --8<---------------cut here---------------start------------->8---
>
> In this paper we have introduced a suite of diagnostic tests for
> language models to better our understanding of the linguistic
> competencies acquired by pre-training via language modeling. We draw our
> tests from psycholinguistic studies, allowing us to target a range of
> linguistic capacities by testing word prediction accuracies and
> sensitivity of model probabilities to linguistic distinctions. As a case
> study, we apply these tests to analyze strengths and weaknesses of the
> popular BERT model, finding that it shows sensitivity to role reversal
> and same-category distinctions, albeit less than humans, and it succeeds
> with noun hypernyms, but it struggles with challenging inferences and
> role-based event prediction—and it shows clear failures with the meaning
> of negation. We make all test sets and experiment code available (see
> Footnote 1), for further experiments.
>
> The capacities targeted by these test sets are by no means
> comprehensive, and future work can build on the foundation of these
> datasets to expand to other aspects of language processing. Because
> these sets are small, we must also be conservative in the strength of
> our conclusions—different formulations may yield different performance,
> and future work can expand to verify the generality of these results. In
> parallel, we hope that the weaknesses highlighted by these diagnostics
> can help to identify areas of need for establishing robust and
> generalizable models for language understanding.
>
> --8<---------------cut here---------------end--------------->8---
>
> Allora ripeto la mia domanda: ci sono nuovi studi che dimostrino che le
> limitazioni evidenziate nei test sulla competenza logico/linguistica di
> BERT siano stati risolti da altri LLM?
>
> Perché credo che sulla _perfomance_ sintattica degli LLM nessuno abbia
> proprio nulla da ridire.
>
> Saluti, 380°
>
> [...]
>
> [1] Message-id: 87o7ux2i16....@xelera.eu
> https://server-nexa.polito.it/pipermail/nexa/2022-September/049508.html
>
>
> --
> 380° (Giovanni Biscuolo public alter ego)
>
> «Noi, incompetenti come siamo,
>  non abbiamo alcun titolo per suggerire alcunché»
>
> Disinformation flourishes because many people care deeply about injustice
> but very few check the facts.  Ask me about <https://stallmansupport.org>.
> _______________________________________________
> nexa mailing list
> nexa@server-nexa.polito.it
> https://server-nexa.polito.it/cgi-bin/mailman/listinfo/nexa
>
_______________________________________________
nexa mailing list
nexa@server-nexa.polito.it
https://server-nexa.polito.it/cgi-bin/mailman/listinfo/nexa

Reply via email to